Seongbeom Park

Nokyung Park

Minjeong Park

Mincheol Chang

Hyunju Yun

Hyun Woo

Hongbeen Park

Haeji Jung

Daewon Chae

Dabin Seo

The Vision & AI (VAI) Lab focuses on advancing artificial intelligence by exploring the role of data. It addresses challenges in computer vision, multi-modal learning, and generative AI. The lab's research interests include data-efficient learning, transfer learning, and synthetic data generation, striving to advance AI systems that learn effectively from limited or imperfect data and push the boundaries of data-driven approaches.

Vision & AI (VAI) Lab은 데이터의 역할을 재고하여 최첨단 인공지능 발전에 기여하는 것을 목표로 한다. 주요 연구 분야는 컴퓨터 비전, 멀티모달 학습, 생성적 AI 등이며, 데이터 효율적인 학습, 전이 학습, 합성 데이터 생성 등을 포함한다. 궁극적으로 제한적이거나 불완전한 데이터로부터 효과적으로 학습할 수 있는 AI 시스템을 발전시키고 데이터 중심 접근 방식을 통해 가능한 영역의 경계를 확장하는 혁신적인 방법 개발에 중점을 둔다.

The main obstacle to weakly supervised semantic image segmentation is the difficulty of obtaining pixel-level information from coarse image-level annotations. Most methods based on image-level annotations use localization maps obtained from the classifier, but these only focus on the small discriminative parts of objects and do not capture precise boundaries. FickleNet explores diverse combinations of locations on feature maps created by generic deep neural networks. It selects hidden units randomly and then uses them to obtain activation scores for image classification. FickleNet implicitly learns the coherence of each location in the feature maps, resulting in a localization map which identifies both discriminative and other parts of objects. The ensemble effects are obtained from a single network by selecting random hidden unit pairs, which means that a variety of localization maps are generated from a single image. Our approach does not require any additional training steps and only adds a simple layer to a standard convolutional neural network; nevertheless it outperforms recent comparable techniques on the Pascal VOC 2012 benchmark in both weakly and semi-supervised settings.

FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inference

Diffusion models learn to restore noisy data, which is corrupted with different levels of noise, by optimizing the weighted sum of the corresponding loss terms, ie, denoising score matching loss. In this paper, we show that restoring data corrupted with certain noise levels offers a proper pretext task for the model to learn rich visual concepts. We propose to prioritize such noise levels over other levels during training, by redesigning the weighting scheme of the objective function. We show that our simple redesign of the weighting scheme significantly improves the performance of diffusion models regardless of the datasets, architectures, and sampling strategies.

Perception Prioritized Training of Diffusion Models

Weakly supervised semantic segmentation produces a pixel-level localization from class labels; but a classifier trained on such labels is likely to restrict its focus to a small discriminative region of the target object. AdvCAM is an attribution map of an image that is manipulated to increase the classification score produced by a classifier. This manipulation is realized in an anti-adversarial manner, which perturbs the original images along pixel gradients in the opposite direction from those used in an adversarial attack. It forces regions initially considered not to be discriminative to become involved in subsequent classifications, and produces attribution maps that successively identify more regions of the target object. In addition, we introduce a new regularization procedure that inhibits both the incorrect attribution of regions unrelated to the target object and excessive concentration of attributions on a small region of that object. Our method is a post-hoc analysis of a trained classifier, which does not need to be altered or retrained. On PASCAL VOC 2012 test images, we achieve mIoUs of 68.0 and 76.9 for weakly and semi-supervised semantic segmentation respectively, which represent a new state-of-the-art.

Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation

Weakly supervised segmentation methods using bounding box annotations focus on obtaining a pixel-level mask from each box containing an object. Existing methods typically depend on a class-agnostic mask generator, which operates on the low-level information intrinsic to an image. In this work, we utilize higher-level information from the behavior of a trained object detector, by seeking the smallest areas of the image from which the object detector produces almost the same result as it does from the whole image. These areas constitute a bounding-box attribution map (BBAM), which identifies the target object in its bounding box and thus serves as pseudo ground-truth for weakly supervised semantic and instance segmentation. This approach significantly outperforms recent comparable techniques on both the PASCAL VOC and MS COCO benchmarks in weakly supervised semantic and instance segmentation. In addition, we provide a detailed analysis of our method, offering deeper insight into the behavior of the BBAM.

BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentation

Weakly supervised semantic segmentation produces pixel-level localization from class labels; however, a classifier trained on such labels is likely to focus on a small discriminative region of the target object. We interpret this phenomenon using the information bottleneck principle: the final layer of a deep neural network, activated by the sigmoid or softmax activation functions, causes an information bottleneck, and as a result, only a subset of the task-relevant information is passed on to the output. We first support this argument through a simulated toy experiment and then propose a method to reduce the information bottleneck by removing the last activation function. In addition, we introduce a new pooling method that further encourages the transmission of information from non-discriminative regions to the classification. Our experimental evaluations demonstrate that this simple modification significantly improves the quality of localization maps on both the PASCAL VOC 2012 and MS COCO 2014 datasets, exhibiting a new state-of-the-art performance for weakly supervised semantic segmentation.

Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation

Weakly supervised semantic segmentation (WSSS) methods are often built on pixel-level localization maps obtained from a classifier. However, training on class labels only, classifiers suffer from the spurious correlation between foreground and background cues (eg train and rail), fundamentally bounding the performance of WSSS methods. There have been previous endeavors to address this issue with additional supervision. We propose a novel source of information to distinguish foreground from the background: Out-of-Distribution (OoD) data, or images devoid of foreground object classes. In particular, we utilize the hard OoDs that the classifier is likely to make false-positive predictions. These samples typically carry key visual features on the background (eg rail) that the classifiers often confuse as the foreground class (eg train). These background cues let classifiers correctly suppress spurious background cues, resulting in an improved pixel-wise map from the classifier. From the cost point of view, acquiring such hard OoDs does not require an extensive amount of annotation efforts; it only incurs a few additional image-level labeling costs on top of the original efforts to collect the weak training set with the image labels. We propose a method, W-OoD, for utilizing the hard OoDs. W-OoD achieves state-of-the-art performance on Pascal VOC 2012. The code is available at: https://github. com/naver-ai/w-ood.

Weakly Supervised Semantic Segmentation using Out-of-Distribution Data

Visual Prompt Tuning (VPT) is an effective tuning method for adapting pretrained Vision Transformers (ViTs) to downstream tasks. It leverages extra learnable tokens, known as prompts, which steer the frozen pretrained ViTs. Although VPT has demonstrated its applicability with supervised vision transformers, it often underperforms with self-supervised ones. Through empirical observations, we deduce that the effectiveness of VPT hinges largely on the ViT blocks with which the prompt tokens interact. Specifically, VPT shows improved performance on image classification tasks for MAE and MoCo v3 when the prompt tokens are inserted into later blocks rather than the first block. These observations suggest that there exists an optimal location of blocks for the insertion of prompt tokens. Unfortunately, identifying the optimal blocks for prompts within each self-supervised ViT for diverse future scenarios is a costly process. To mitigate this problem, we propose a simple yet effective method that learns a gate for each ViT block to adjust its intervention into the prompt tokens. With our method, prompt tokens are selectively influenced by blocks that require steering for task adaptation. Our method outperforms VPT variants in FGVC and VTAB image classification and ADE20K semantic segmentation. The code is available at https://github. com/ryongithub/GatedPromptTuning.

Improving Visual Prompt Tuning for Self-supervised Vision Transformers

Weakly supervised object localization aims to find a target object region in a given image with only weak supervision, such as image-level labels. Most existing methods use a class activation map (CAM) to generate a localization map; however, a CAM identifies only the most discriminative parts of a target object rather than the entire object region. In this work, we find the gap between classification and localization in terms of the misalignment of the directions between an input feature and a class-specific weight. We demonstrate that the misalignment suppresses the activation of CAM in areas that are less discriminative but belong to the target object. To bridge the gap, we propose a method to align feature directions with a class-specific weight. The proposed method achieves a state-of-the-art localization performance on the CUB-200-2011 and ImageNet-1K benchmarks.

Bridging the Gap between Classification and Localization for Weakly Supervised Object Localization

When a deep neural network is trained on data with only image-level labeling, the regions activated in each image tend to identify only a small region of the target object. We propose a method of using videos automatically harvested from the web to identify a larger region of the target object by using temporal information, which is not present in the static image. The temporal variations in a video allow different regions of the target object to be activated. We obtain an activated region in each frame of a video, and then aggregate the regions from successive frames into a single image, using a warping technique based on optical flow. The resulting localization maps cover more of the target object, and can then be used as proxy ground-truth to train a segmentation network. This simple approach outperforms existing methods under the same level of supervision, and even approaches relying on extra annotations. Based on VGG-16 and ResNet 101 backbones, our method achieves the mIoU of 65.0 and 67.4, respectively, on PASCAL VOC 2012 test images, which represents a new state-of-the-art.

Frame-to-Frame Aggregation of Active Regions in Web Videos for Weakly Supervised Semantic Segmentation

A meningioma is a type of brain tumor that requires tumor volume size follow ups in order to reach appropriate clinical decisions. A fully automated tool for meningioma detection is necessary for reliable and consistent tumor surveillance. There have been various studies concerning automated lesion detection. Studies on the application of convolutional neural network (CNN)-based methods, which have achieved a state-of-the-art level of performance in various computer vision tasks, have been carried out. However, the applicable diseases are limited, owing to a lack of strongly annotated data being present in medical image analysis. In order to resolve the above issue we propose pyramid gradient-based class activation mapping (PG-CAM) which is a novel method for tumor localization that can be trained in weakly supervised manner. PG-CAM uses a densely connected encoder-decoder-based feature pyramid network (DC-FPN) as a backbone structure, and extracts a multi-scale Grad-CAM that captures hierarchical features of a tumor. We tested our model using meningioma brain magnetic resonance (MR) data collected from the collaborating hospital. In our experiments, PG-CAM outperformed Grad-CAM by delivering a 23 percent higher localization accuracy for the validation set.

Robust tumor localization with pyramid grad-cam

Obtaining accurate pixel-level localization from class labels is a crucial process in weakly supervised semantic segmentation and object localization. Attribution maps from a trained classifier are widely used to provide pixel-level localization, but their focus tends to be restricted to a small discriminative region of the target object. An AdvCAM is an attribution map of an image that is manipulated to increase the classification score produced by a classifier before the final softmax or sigmoid layer. This manipulation is realized in an anti-adversarial manner, so that the original image is perturbed along pixel gradients in directions opposite to those used in an adversarial attack. This process enhances non-discriminative yet class-relevant features, which make an insufficient contribution to previous attribution maps, so that the resulting AdvCAM identifies more regions of the target object. In addition, we introduce a new …

Anti-Adversarially Manipulated Attributions for Weakly Supervised Semantic Segmentation and Object Localization

Referring image segmentation (RIS) aims to localize the object in an image referred by a natural language expression. Most previous studies learn RIS with a large-scale dataset containing segmentation labels, but they are costly. We present a weakly supervised learning method for RIS that only uses readily available image-text pairs. We first train a visual-linguistic model for image-text matching and extract a visual saliency map through Grad-CAM to identify the image regions corresponding to each word. However, we found two major problems with Grad-CAM. First, it lacks consideration of critical semantic relationships between words. We tackle this problem by modeling the relationship between words through intra-chunk and inter-chunk consistency. Second, Grad-CAM identifies only small regions of the referred object, leading to low recall. Therefore, we refine the localization maps with self-attention in Transformer and unsupervised object shape prior. On three popular benchmarks (RefCOCO, RefCOCO+, G-Ref), our method significantly outperforms recent comparable techniques. We also show that our method is applicable to various levels of supervision and obtains better performance than recent methods.

Weakly Supervised Referring Image Segmentation with Intra-Chunk and Inter-Chunk Consistency

The extraction of meaningful features from videos is important as they can be used in various applications. Despite its importance, video representation learning has not been studied much, because it is challenging to deal with both content and motion information. We present a Mutual Suppression network (MSnet) to learn disentangled motion and content features in videos. The MSnet is trained in such way that content features do not contain motion information and motion features do not contain content information; this is done by suppressing each other with adversarial training. We utilize the disentangled features from the MSnet for several tasks, such as frame reproduction, pixel-level video frame prediction, and dense optical flow estimation, to demonstrate the strength of MSnet. The proposed model outperforms the state-of-the-art methods in pixel-level video frame prediction. The source code will be publicly available.

Msnet: Mutual suppression network for disentangled video representations

Recent image generation models show remarkable generation performance. However, they mirror strong location preference in datasets, which we call spatial bias. Therefore, generators render poor samples at unseen locations and scales. We argue that the generators rely on their implicit positional encoding to render spatial content. From our observations, the generator's implicit positional encoding is translation-variant, making the generator spatially biased. To address this issue, we propose injecting explicit positional encoding at each scale of the generator. By learning the spatially unbiased generator, we facilitate the robust use of generators in multiple tasks, such as GAN inversion, multi-scale generation, generation of arbitrary sizes and aspect ratios. Furthermore, we show that our method can also be applied to denoising diffusion probabilistic models.

Toward Spatially Unbiased Generative Models

While CLIP has significantly advanced multimodal understanding by bridging vision and language, the inability to grasp negation--such as failing to differentiate concepts like" parking" from" no parking"--poses substantial challenges. By analyzing the data used in the public CLIP model's pre-training, we posit this limitation stems from a lack of negation-inclusive data. To address this, we introduce data generation pipelines that employ a large language model (LLM) and a multimodal LLM to produce negation-inclusive captions. Fine-tuning CLIP with data generated from our pipelines, we develop NegationCLIP, which enhances negation awareness while preserving the generality. Moreover, to enable a comprehensive evaluation of negation understanding, we propose NegRefCOCOg--a benchmark tailored to test VLMs' ability to interpret negation across diverse expressions and positions within a sentence. Experiments on various CLIP architectures validate the effectiveness of our data generation pipelines in enhancing CLIP's ability to perceive negation accurately. Additionally, NegationCLIP's enhanced negation awareness has practical applications across various multimodal tasks, demonstrated by performance gains in text-to-image generation and referring image segmentation.

Know" No" Better: A Data-Driven Approach for Enhancing Negation Awareness in CLIP

Recent Vision-Language Pre-training (VLP) models have demonstrated significant advancements. Nevertheless, these models heavily rely on image-text pairs that capture only coarse and global information of an image, leading to a limitation in their regional understanding ability. In this work, we introduce RegionVLM, equipped with explicit regional modeling capabilities, allowing them to understand user-indicated image regions. To achieve this, we design a simple yet innovative architecture, requiring no modifications to the model architecture or objective function. Additionally, we leverage a dataset that contains a novel source of information, namely Localized Narratives, which has been overlooked in previous VLP research. Our experiments demonstrate that our single generalist model not only achieves an interactive dialogue system but also exhibits superior performance on various zero-shot region understanding tasks, without compromising its ability for global image understanding.

Toward Interactive Regional Understanding in Vision-Large Language Models

Recent text-to-image diffusion models generate high-quality images but struggle to learn new styles, which limits the personalized content creation. In response, style-driven generation has become a popular task, wherein users supply reference images capturing the target style, complemented by text prompts that specify stylistic cues. Fine-tuning is a common approach, yet it often blindly utilizes pre-training configurations without modification, especially for noise schedules defined in terms of signal-to-noise ratio (SNR), which determines the amount of image information available at each denoising step. We discover that stylistic features predominantly emerge at low SNR range, leading current fine-tuning methods using regular noise schedules to exhibit suboptimal style alignment. We propose the Style-friendly SNR sampler, which focuses the fine-tuning on low SNR range where stylistic features emerge. We demonstrate improved generation of novel styles that cannot be described solely with a text prompt, enabling high-fidelity personalized content creation.

Style-friendly snr sampler for style-driven generation

We present Subject Fidelity Optimization (SFO), a novel comparative learning framework for zero-shot subject-driven generation that enhances subject fidelity. Existing supervised fine-tuning methods, which rely only on positive targets and use the diffusion loss as in the pre-training stage, often fail to capture fine-grained subject details. To address this, SFO introduces additional synthetic negative targets and explicitly guides the model to favor positives over negatives through pairwise comparison. For negative targets, we propose Condition-Degradation Negative Sampling (CDNS), which automatically produces synthetic negatives tailored for subject-driven generation by introducing controlled degradations that emphasize subject fidelity and text alignment without expensive human annotations. Moreover, we reweight the diffusion timesteps to focus fine-tuning on intermediate steps where subject details emerge. Extensive experiments demonstrate that SFO with CDNS significantly outperforms recent strong baselines in terms of both subject fidelity and text alignment on a subject-driven generation benchmark. Project page: https://subjectfidelityoptimization.github.io/

Negative-Guided Subject Fidelity Optimization for Zero-Shot Subject-Driven Generation

Deep neural perception and control networks have become key components of self-driving vehicles. User acceptance is likely to benefit from easy-to-interpret textual explanations which allow end-users to understand what triggered a particular behavior. Explanations may be triggered by the neural controller, namely introspective explanations, or informed by the neural controller's output, namely rationalizations. We propose a new approach to introspective explanations which consists of two parts. First, we use a visual (spatial) attention model to train a convolutional network end-to-end from images to the vehicle control commands, ie, acceleration and change of course. The controller's attention identifies image regions that potentially influence the network's output. Second, we use an attention-based video-to-text model to produce textual explanations of model actions. The attention maps of controller and explanation model are aligned so that explanations are grounded in the parts of the scene that mattered to the controller. We explore two approaches to attention alignment, strong-and weak-alignment. Finally, we explore a version of our model that generates rationalizations, and compare with introspective explanations on the same video segments. We evaluate these models on a novel driving dataset with ground-truth human explanations, the Berkeley DeepDrive eXplanation (BDD-X) dataset. Code is available at https://github. com/JinkyuKimUCB/explainable-deep-driving.

Textual explanations for self-driving vehicles

Deep neural perception and control networks are likely to be a key component of self-driving vehicles. These models need to be explainable-they should provide easy-to-interpret rationales for their behavior-so that passengers, insurance companies, law enforcement, developers etc., can understand what triggered a particular behavior. Here we explore the use of visual explanations. These explanations take the form of real-time highlighted regions of an image that causally influence the network's output (steering control). Our approach is two-stage. In the first stage, we use a visual attention model to train a convolution network end-to-end from images to steering angle. The attention model highlights image regions that potentially influence the network's output. Some of these are true influences, but some are spurious. We then apply a causal filtering step to determine which input regions actually influence the output. This produces more succinct visual explanations and more accurately exposes the network's behavior. We demonstrate the effectiveness of our model on three datasets totaling 16 hours of driving. We first show that training with attention does not degrade the performance of the end-to-end network. Then we show that the network causally cues on a variety of features that are used by humans while driving.

Interpretable learning for self-driving cars by visualizing causal attention

In general, an experimental environment for deep learning assumes that the training and the test dataset are sampled from the same distribution. However, in real-world situations, a difference in the distribution between two datasets, ie domain shift, may occur, which becomes a major factor impeding the generalization performance of the model. The research field to solve this problem is called domain generalization, and it alleviates the domain shift problem by extracting domain-invariant features explicitly or implicitly. In recent studies, contrastive learning-based domain generalization approaches have been proposed and achieved high performance. These approaches require sampling of the negative data pair. However, the performance of contrastive learning fundamentally depends on quality and quantity of negative data pairs. To address this issue, we propose a new regularization method for domain generalization based on contrastive learning, called self-supervised contrastive regularization (SelfReg). The proposed approach uses only positive data pairs, thus it resolves various problems caused by negative pair sampling. Moreover, we propose a class-specific domain perturbation layer (CDPL), which makes it possible to effectively apply mixup augmentation even when only positive data pairs are used. The experimental results show that the techniques incorporated by SelfReg contributed to the performance in a compatible manner. In the recent benchmark, DomainBed, the proposed method shows comparable performance to the conventional state-of-the-art alternatives.

Selfreg: Self-supervised contrastive regularization for domain generalization

Robust driver attention prediction for critical situations is a challenging computer vision problem, yet essential for autonomous driving. Because critical driving moments are so rare, collecting enough data for these situations is difficult with the conventional in-car data collection protocol—tracking eye movements during driving. Here, we first propose a new in-lab driver attention collection protocol and introduce a new driver attention dataset, Berkeley DeepDrive Attention (BDD-A) dataset, which is built upon braking event videos selected from a large-scale, crowd-sourced driving video dataset. We further propose Human Weighted Sampling (HWS) method, which uses human gaze behavior to identify crucial frames of a driving dataset and weights them heavily during model training. With our dataset and HWS, we built a driver attention prediction model that outperforms the state-of-the-art and demonstrates …

Predicting driver attention in critical situations

Recent success suggests that deep neural control networks are likely to be a key component of self-driving vehicles. These networks are trained on large datasets to imitate human actions, but they lack semantic understanding of image contents. This makes them brittle and potentially unsafe in situations that do not match training data. Here, we propose to address this issue by augmenting training data with natural language advice from a human. Advice includes guidance about what to do and where to attend. We present the first step toward advice giving, where we train an end-to-end vehicle controller that accepts advice. The controller adapts the way it attends to the scene (visual attention) and the control (steering and speed). Attention mechanisms tie controller behavior to salient objects in the advice. We evaluate our model on a novel advisable driving dataset with manually annotated human-to-vehicle advice called Honda Research Institute-Advice Dataset (HAD). We show that taking advice improves the performance of the end-to-end network, while the network cues on a variety of visual features that are provided by advice. The dataset is available at https://usa. honda-ri. com/HAD.

Grounding human-to-vehicle advice for self-driving vehicles

Motivation: Capillary electrophoresis (CE) of nucleic acids is a workhorse technology underlying high-throughput genome analysis and large-scale chemical mapping for nucleic acid structural inference. Despite the wide availability of CE-based instruments, there remain challenges in leveraging their full power for quantitative analysis of RNA and DNA structure, thermodynamics and kinetics. In particular, the slow rate and poor automation of available analysis tools have bottlenecked a new generation of studies involving hundreds of CE profiles per experiment. Results: We propose a computational method called high-throughput robust analysis for capillary electrophoresis (HiTRACE) to automate the key tasks in large-scale nucleic acid CE analysis, including the profile alignment that has heretofore been a rate-limiting step in the highest throughput experiments. We illustrate the application of …

HiTRACE: high-throughput robust analysis for capillary electrophoresis

We propose Occupancy Flow Fields, a new representation for motion forecasting of multiple agents, an important task in autonomous driving.Our representation is a spatio-temporal grid with each grid cell containing both the probability of the cell being occupied by any agent, and a two-dimensional flow vector representing the direction and magnitude of the motion in that cell. Our method successfully mitigates shortcomings of the two most commonly-used representations for motion forecasting: trajectory sets and occupancy grids. Although occupancy grids efficiently represent the probabilistic location of many agents jointly, they do not capture agent motion and lose the agent identities. To this end, we propose a deep learning architecture that generates Occupancy Flow Fields with the help of a new flow trace loss that establishes consistency between the occupancy and flow predictions. We demonstrate the …

Occupancy flow fields for motion forecasting in autonomous driving

The recent success of the generative model shows that leveraging the multi-modal embedding space can manipulate an image using text information. However, manipulating an image with other sources rather than text, such as sound, is not easy due to the dynamic characteristics of the sources. Especially, sound can convey vivid emotions and dynamic expressions of the real world. Here, we propose a framework that directly encodes sound into the multi-modal (image-text) embedding space and manipulates an image from the space. Our audio encoder is trained to produce a latent representation from an audio input, which is forced to be aligned with image and text representations in the multi-modal embedding space. We use a direct latent optimization method based on aligned embeddings for sound-guided image manipulation. We also show that our method can mix different modalities, ie, text and audio, which enrich the variety of the image modification. The experiments on zero-shot audio classification and semantic-level image classification show that our proposed model outperforms other text and sound-guided state-of-the-art methods.

Sound-guided semantic image manipulation

The recent success in StyleGAN demonstrates that pre-trained StyleGAN latent space is useful for realistic video generation. However, the generated motion in the video is usually not semantically meaningful due to the difficulty of determining the direction and magnitude in the StyleGAN latent space. In this paper, we propose a framework to generate realistic videos by leveraging multimodal (sound-image-text) embedding space. As sound provides the temporal contexts of the scene, our framework learns to generate a video that is semantically consistent with sound. First, our sound inversion module maps the audio directly into the StyleGAN latent space. We then incorporate the CLIP-based multimodal embedding space to further provide the audio-visual relationships. Finally, the proposed frame generator learns to find the trajectory in the latent space which is coherent with the corresponding sound and …

Sound-guided semantic video generation

Humans learn to drive through both practice and theory, eg by studying the rules, while most self-driving systems are limited to the former. Being able to incorporate human knowledge of typical causal driving behaviour should benefit autonomous systems. We propose a new approach that learns vehicle control with the help of human advice. Specifically, our system learns to summarize its visual observations in natural language, predict an appropriate action response (eg" I see a pedestrian crossing, so I stop"), and predict the controls, accordingly. Moreover, to enhance interpretability of our system, we introduce a fine-grained attention mechanism which relies on semantic segmentation and object-centric RoI pooling. We show that our approach of training the autonomous system with human advice, grounded in a rich semantic representation, matches or outperforms prior work in terms of control prediction and explanation generation. Our approach also results in more interpretable visual explanations by visualizing object-centric attention maps. Code is available at https://github. com/JinkyuKimUCB/advisable-driving.

Advisable learning for self-driving vehicles by internalizing observation-to-action rules

Inspired by human vision, we propose a new periphery-fovea multi-resolution driving model that predicts vehicle speed from dash camera videos. The peripheral vision module of the model processes the full video frames in low resolution with large receptive fields. Its foveal vision module selects sub-regions and uses high-resolution input from those regions to improve its driving performance. We train the fovea selection module with supervision from driver gaze. We show that adding high-resolution input from predicted human driver gaze locations significantly improves the driving accuracy of the model. Our periphery-fovea multi-resolution model outperforms a uni-resolution periphery-only model that has the same amount of floating-point operations. More importantly, we demonstrate that our driving model achieves a significantly higher performance gain in pedestrian-involved critical situations than in other non-critical situations. Our code is publicly available at https://github. com/pascalxia/periphery_fovea_driving.

Periphery-fovea multi-resolution driving model guided by human attention

Traffic lights perception problem is one of the key challenges for autonomous vehicle controllers in urban areas. While a number of approaches for traffic light detection have been proposed, these methods often require a prior knowledge of map and/or show high false positive rates. Recent successes suggest that deep neural networks will be widely used in self-driving cars, but current public datasets do not provide sufficient amount of labels for training such large deep neural networks. In this paper, we developed a two-step computational method that can detect traffic lights from images in a real-time manner. The first step exploits a deep neural object detection architecture to fine true traffic light candidates. In the second step, a point-based reward system is used to eliminate false traffic lights out of the candidates. To evaluate the proposed approach, we collected a human-annotated large-scale traffic lights …

Deep traffic light detection for self-driving cars from a large-scale dataset

Reducing the representational discrepancy between source and target domains is a key component to maximize the model generalization. In this work, we advocate for leveraging natural language supervision for the domain generalization task. We introduce two modules to ground visual representations with texts containing typical reasoning of humans: (1) Visual and Textual Joint Embedder and (2) Textual Explanation Generator . The former learns the image-text joint embedding space where we can ground high-level class-discriminative information into the model. The latter leverages an explainable model and generates explanations justifying the rationale behind its decision. To the best of our knowledge, this is the first work to leverage the vision-and-language cross-modality approach for the domain generalization task. Our experiments with a newly created CUB-DG benchmark dataset demonstrate that cross …

Grounding visual representations with texts for domain generalization

In recent years, video generation has become a prominent generative tool and has drawn significant attention. However, there is little consideration in audio-to-video generation, though audio contains unique qualities like temporal semantics and magnitude. Hence, we propose The Power of Sound (TPoS) model to incorporate audio input that includes both changeable temporal semantics and magnitude. To generate video frames, TPoS utilizes a latent stable diffusion model with textual semantic information, which is then guided by the sequential audio embedding from our pretrained Audio Encoder. As a result, this method produces audio reactive video contents. We demonstrate the effectiveness of TPoS across various tasks and compare its results with current state-of-the-art techniques in the field of audio-to-video generation. More examples are available at https://ku-vai. github. io/TPoS/

The power of sound (tpos): Audio reactive video generation with stable diffusion

As a great deal of data has been accumulated in various disciplines, the need for the integrative analysis of separate but relevant data sources is becoming more important. Combining data sources can provide global insight that is otherwise difficult to obtain from individual sources. Because of privacy, regulations, and other issues, many large-scale data repositories remain closed off from the outside, raising what has been termed the data silo issue. The huge volume of today's big data often leads to computational challenges, adding another layer of complexity to the solution. In this paper, we propose a novel method called collaborative analytics by ensemble learning (CABEL), which attempts to resolve the main hurdles regarding the silo issue: accuracy, privacy, and computational efficiency. CABEL represents the data stored in each silo as a compact aggregate of samples called the silo signature. The compact …

Collaborative analytics for data silos

The assessment of information transfer in the global economic network helps to understand the current environment and the outlook of an economy. Most approaches on global networks extract information transfer based mainly on a single variable. This paper establishes an entirely new bioinformatics-inspired approach to integrating information transfer derived from multiple variables and develops an international economic network accordingly. In the proposed methodology, we first construct the transfer entropies (TEs) between various intra- and inter-country pairs of economic time series variables, test their significances, and then use a weighted sum approach to aggregate information captured in each TE. Through a simulation study, the new method is shown to deliver better information integration compared to existing integration methods in that it can be applied even when intra-country variables are correlated. Empirical investigation with the real world data reveals that Western countries are more influential in the global economic network and that Japan has become less influential following the Asian currency crisis.

Entropy-based analysis and bioinformatics-inspired integration of global economic information transfer

We introduce a novel diffusion-based video generation method, generating a video showing multiple events given multiple individual sentences from the user. Our method does not require a large-scale video dataset since our method uses a pre-trained diffusion-based text-to-video generative model without a fine-tuning process. Specifically, we propose a last frame-aware diffusion process to preserve visual coherence between consecutive videos where each video consists of different events by initializing the latent and simultaneously adjusting noise in the latent to enhance the motion dynamic in a generated video. Furthermore, we find that the iterative update of latent vectors by referring to all the preceding frames maintains the global appearance across the frames in a video clip. To handle dynamic text input for video generation, we utilize a novel prompt generator that transfers course text messages from the …

Mevg: Multi-event video generation with text-to-video models

Social relations have substantial impacts on the potential trajectories of each individual. Modeling these dynamics has been a central solution for more precise and accurate trajectory forecasting. However previous works ignore the importance ofsocial depth'meaning the influences flowing from different degrees of social relations. In this work we propose HighGraph a graph-based pedestrian relational reasoning method that captures the higher-order dynamics of social interactions. First we construct a collision-aware relation graph based on the agents' observed trajectories. Upon this graph structure we build our core module that aggregates the agent features from diverse social distances. As a result the network is able to model complex social relations thereby yielding more accurate and socially acceptable trajectories. Our HighGraph is a plug-and-play module that can be easily applied to any current trajectory predictors. Extensive experiments with ETH/UCY and SDD datasets demonstrate that our HighGraph noticeably improves the previous state-of-the-art baselines both quantitatively and qualitatively.

Higher-order relational reasoning for pedestrian trajectory prediction

Humans learn to drive through both practice and theory, for example, by studying the rules, while most self‐driving systems are limited to the former. Being able to incorporate human knowledge of typical causal driving behavior should benefit autonomous systems. We propose a new approach that learns vehicle control with the help of human advice. Specifically, our system learns to summarize its visual observations in natural language, predict an appropriate action response (eg, “I see a pedestrian crossing, so I stop”), and predict the controls, accordingly. Moreover, to enhance the interpretability of our system, we introduce a fine‐grained attention mechanism that relies on semantic segmentation and object‐centric RoI pooling. We show that our approach of training the autonomous system with human advice, grounded in a rich semantic representation, matches or outperforms prior work in terms of control …

Toward explainable and advisable model for self‐driving cars

We introduce a motion forecasting (behavior prediction) method that meets the latency requirements for autonomous driving in dense urban environments without sacrificing accuracy. A whole-scene sparse input representation allows StopNet to scale to predicting trajectories for hundreds of road agents with reliable latency. In addition to predicting trajectories, our scene encoder lends itself to predicting whole-scene probabilistic occupancy grids, a complementary output representation suitable for busy urban environments. Occupancy grids allow the AV to reason collectively about the behavior of groups of agents without processing their individual trajectories. We demonstrate the effectiveness of our sparse input representation and our model in terms of computation and accuracy over three datasets. We further show that co-training consistent trajectory and occupancy predictions improves upon state-of-the-art …

Vision & AI Lab

교수님 소개

이정범

연구실 소개

연구실 키워드

알럼나이가 간 회사

연구실 지원 방법

대우 조건

연도별 논문 인용수

저널 & 학회 논문 출판 수

연구실 논문 목록

FlowFixer: Towards Detail-Preserving Subject-Driven Generation

Focus, Don’t Prune: Identifying Instruction-Relevant Regions for Information-Rich Image Understanding

Image-Guided Semantic Pseudo-LiDAR Point Generation for 3D Object Detection

연구실 보유 특허

대학별 입시끈

우리 연구실 모집