In So Kweon

Dahun Kim, Jun Xie, Huiyu Wang et al. · deepmind

We present TubeFormer-DeepLab, the first attempt to tackle multiple core video segmentation tasks in a unified manner. Different video segmentation tasks (e.g., video semantic/instance/panoptic segmentation) are usually considered as distinct problems. State-of-the-art models adopted in the separate communities have diverged, and radically different approaches dominate in each task. By contrast, we make a crucial observation that video segmentation tasks could be generally formulated as the problem of assigning different predicted labels to video tubes (where a tube is obtained by linking segmentation masks along the time axis) and the labels may encode different values depending on the target task. The observation motivates us to develop TubeFormer-DeepLab, a simple and effective video mask transformer model that is widely applicable to multiple video segmentation tasks. TubeFormer-DeepLab directly predicts video tubes with task-specific labels (either pure semantic categories, or both semantic categories and instance identities), which not only significantly simplifies video segmentation models, but also advances state-of-the-art results on multiple video segmentation benchmarks

Chaoning Zhang, Kang Zhang, Chenshuang Zhang et al.

Adversarial training (AT) for robust representation learning and self-supervised learning (SSL) for unsupervised representation learning are two active research fields. Integrating AT into SSL, multiple prior works have accomplished a highly significant yet challenging task: learning robust representation without labels. A widely used framework is adversarial contrastive learning which couples AT and SSL, and thus constitute a very complex optimization problem. Inspired by the divide-and-conquer philosophy, we conjecture that it might be simplified as well as improved by solving two sub-problems: non-robust SSL and pseudo-supervised AT. This motivation shifts the focus of the task from seeking an optimal integrating strategy for a coupled problem to finding sub-solutions for sub-problems. With this said, this work discards prior practices of directly introducing AT to SSL frameworks and proposed a two-stage framework termed Decoupled Adversarial Contrastive Learning (DeACL). Extensive experimental results demonstrate that our DeACL achieves SOTA self-supervised adversarial robustness while significantly reducing the training time, which validates its effectiveness and efficiency. Moreover, our DeACL constitutes a more explainable solution, and its success also bridges the gap with semi-supervised AT for exploiting unlabeled samples for robust representation learning. The code is publicly accessible at https://github.com/pantheon5100/DeACL.

Fei Pan, Xu Yin, Seokju Lee et al.

Unsupervised domain adaptation (UDA) has been a potent technique to handle the lack of annotations in the target domain, particularly in semantic segmentation task. This study introduces a different UDA scenarios where the target domain contains unlabeled video frames. Drawing upon recent advancements of self-supervised learning of the object motion from unlabeled videos with geometric constraint, we design a \textbf{Mo}tion-guided \textbf{D}omain \textbf{A}daptive semantic segmentation framework (MoDA). MoDA harnesses the self-supervised object motion cues to facilitate cross-domain alignment for segmentation task. First, we present an object discovery module to localize and segment target moving objects using object motion information. Then, we propose a semantic mining module that takes the object masks to refine the pseudo labels in the target domain. Subsequently, these high-quality pseudo labels are used in the self-training loop to bridge the cross-domain gap. On domain adaptive video and image segmentation experiments, MoDA shows the effectiveness utilizing object motion as guidance for domain alignment compared with optical flow information. Moreover, MoDA exhibits versatility as it can complement existing state-of-the-art UDA approaches. Code at https://github.com/feipanir/MoDA.

Ukcheol Shin, Kyunghyun Lee, In So Kweon et al.

RGB-thermal semantic segmentation is one potential solution to achieve reliable semantic scene understanding in adverse weather and lighting conditions. However, the previous studies mostly focus on designing a multi-modal fusion module without consideration of the nature of multi-modality inputs. Therefore, the networks easily become over-reliant on a single modality, making it difficult to learn complementary and meaningful representations for each modality. This paper proposes 1) a complementary random masking strategy of RGB-T images and 2) self-distillation loss between clean and masked input modalities. The proposed masking strategy prevents over-reliance on a single modality. It also improves the accuracy and robustness of the neural network by forcing the network to segment and classify objects even when one modality is partially available. Also, the proposed self-distillation loss encourages the network to extract complementary and meaningful representations from a single modality or complementary masked modalities. Based on the proposed method, we achieve state-of-the-art performance over three RGB-T semantic segmentation benchmarks. Our source code is available at https://github.com/UkcheolShin/CRM_RGBTSeg.

Chaoning Zhang, Chenshuang Zhang, Sheng Zheng et al.

As ChatGPT goes viral, generative AI (AIGC, a.k.a AI-generated content) has made headlines everywhere because of its ability to analyze and create text, images, and beyond. With such overwhelming media coverage, it is almost impossible for us to miss the opportunity to glimpse AIGC from a certain angle. In the era of AI transitioning from pure analysis to creation, it is worth noting that ChatGPT, with its most recent language model GPT-4, is just a tool out of numerous AIGC tasks. Impressed by the capability of the ChatGPT, many people are wondering about its limits: can GPT-5 (or other future GPT variants) help ChatGPT unify all AIGC tasks for diversified content creation? Toward answering this question, a comprehensive review of existing AIGC tasks is needed. As such, our work comes to fill this gap promptly by offering a first look at AIGC, ranging from its techniques to applications. Modern generative AI relies on various technical foundations, ranging from model architecture and self-supervised pretraining to generative modeling methods (like GAN and diffusion models). After introducing the fundamental techniques, this work focuses on the technological development of various AIGC tasks based on their output type, including text, images, videos, 3D content, etc., which depicts the full potential of ChatGPT's future. Moreover, we summarize their significant applications in some mainstream industries, such as education and creativity content. Finally, we discuss the challenges currently faced and present an outlook on how generative AI might evolve in the near future.

Taehoon Kim, Pyunghwan Ahn, Sangyun Kim et al. · nvidia, utoronto

In this report, we introduce NICE (New frontiers for zero-shot Image Captioning Evaluation) project and share the results and outcomes of 2023 challenge. This project is designed to challenge the computer vision community to develop robust image captioning models that advance the state-of-the-art both in terms of accuracy and fairness. Through the challenge, the image captioning models were tested using a new evaluation dataset that includes a large variety of visual concepts from many domains. There was no specific training data provided for the challenge, and therefore the challenge entries were required to adapt to new types of image descriptions that had not been seen during training. This report includes information on the newly proposed NICE dataset, evaluation methods, challenge results, and technical details of top-ranking entries. We expect that the outcomes of the challenge will contribute to the improvement of AI models on various vision-language tasks.

Sanghyun Woo, Shoubhik Debnath, Ronghang Hu et al.

Driven by improved architectures and better representation learning frameworks, the field of visual recognition has enjoyed rapid modernization and performance boost in the early 2020s. For example, modern ConvNets, represented by ConvNeXt, have demonstrated strong performance in various scenarios. While these models were originally designed for supervised learning with ImageNet labels, they can also potentially benefit from self-supervised learning techniques such as masked autoencoders (MAE). However, we found that simply combining these two approaches leads to subpar performance. In this paper, we propose a fully convolutional masked autoencoder framework and a new Global Response Normalization (GRN) layer that can be added to the ConvNeXt architecture to enhance inter-channel feature competition. This co-design of self-supervised learning techniques and architectural improvement results in a new model family called ConvNeXt V2, which significantly improves the performance of pure ConvNets on various recognition benchmarks, including ImageNet classification, COCO detection, and ADE20K segmentation. We also provide pre-trained ConvNeXt V2 models of various sizes, ranging from an efficient 3.7M-parameter Atto model with 76.7% top-1 accuracy on ImageNet, to a 650M Huge model that achieves a state-of-the-art 88.9% accuracy using only public training data.

Chenshuang Zhang, Chaoning Zhang, Mengchun Zhang et al.

This survey reviews the progress of diffusion models in generating images from text, ~\textit{i.e.} text-to-image diffusion models. As a self-contained work, this survey starts with a brief introduction of how diffusion models work for image synthesis, followed by the background for text-conditioned image synthesis. Based on that, we present an organized review of pioneering methods and their improvements on text-to-image generation. We further summarize applications beyond image generation, such as text-guided generation for various modalities like videos, and text-guided image editing. Beyond the progress made so far, we discuss existing challenges and promising future directions.

Axi Niu, Pham Xuan Trung, Kang Zhang et al.

Diffusion models have gained significant popularity in the field of image-to-image translation. Previous efforts applying diffusion models to image super-resolution (SR) have demonstrated that iteratively refining pure Gaussian noise using a U-Net architecture trained on denoising at various noise levels can yield satisfactory high-resolution images from low-resolution inputs. However, this iterative refinement process comes with the drawback of low inference speed, which strongly limits its applications. To speed up inference and further enhance the performance, our research revisits diffusion models in image super-resolution and proposes a straightforward yet significant diffusion model-based super-resolution method called ACDMSR (accelerated conditional diffusion model for image super-resolution). Specifically, our method adapts the standard diffusion model to perform super-resolution through a deterministic iterative denoising process. Our study also highlights the effectiveness of using a pre-trained SR model to provide the conditional image of the given low-resolution (LR) image to achieve superior high-resolution results. We demonstrate that our method surpasses previous attempts in qualitative and quantitative results through extensive experiments conducted on benchmark datasets such as Set5, Set14, Urban100, BSD100, and Manga109. Moreover, our approach generates more visually realistic counterparts for low-resolution images, emphasizing its effectiveness in practical scenarios.

M. Jehanzeb Mirza, Inkyu Shin, Wei Lin et al.

Our MATE is the first Test-Time-Training (TTT) method designed for 3D data, which makes deep networks trained for point cloud classification robust to distribution shifts occurring in test data. Like existing TTT methods from the 2D image domain, MATE also leverages test data for adaptation. Its test-time objective is that of a Masked Autoencoder: a large portion of each test point cloud is removed before it is fed to the network, tasked with reconstructing the full point cloud. Once the network is updated, it is used to classify the point cloud. We test MATE on several 3D object classification datasets and show that it significantly improves robustness of deep networks to several types of corruptions commonly occurring in 3D point clouds. We show that MATE is very efficient in terms of the fraction of points it needs for the adaptation. It can effectively adapt given as few as 5% of tokens of each test sample, making it extremely lightweight. Our experiments show that MATE also achieves competitive performance by adapting sparsely on the test data, which further reduces its computational overhead, making it ideal for real-time applications.

Axi Niu, Kang Zhang, Trung X. Pham et al.

Diffusion probabilistic models (DPM) have been widely adopted in image-to-image translation to generate high-quality images. Prior attempts at applying the DPM to image super-resolution (SR) have shown that iteratively refining a pure Gaussian noise with a conditional image using a U-Net trained on denoising at various-level noises can help obtain a satisfied high-resolution image for the low-resolution one. To further improve the performance and simplify current DPM-based super-resolution methods, we propose a simple but non-trivial DPM-based super-resolution post-process framework,i.e., cDPMSR. After applying a pre-trained SR model on the to-be-test LR image to provide the conditional input, we adapt the standard DPM to conduct conditional image generation and perform super-resolution through a deterministic iterative denoising process. Our method surpasses prior attempts on both qualitative and quantitative results and can generate more photo-realistic counterparts for the low-resolution images with various benchmark datasets including Set5, Set14, Urban100, BSD100, and Manga109. Code will be published after accepted.

Chaoning Zhang, Chenshuang Zhang, Chenghao Li et al.

OpenAI has recently released GPT-4 (a.k.a. ChatGPT plus), which is demonstrated to be one small step for generative AI (GAI), but one giant leap for artificial general intelligence (AGI). Since its official release in November 2022, ChatGPT has quickly attracted numerous users with extensive media coverage. Such unprecedented attention has also motivated numerous researchers to investigate ChatGPT from various aspects. According to Google scholar, there are more than 500 articles with ChatGPT in their titles or mentioning it in their abstracts. Considering this, a review is urgently needed, and our work fills this gap. Overall, this work is the first to survey ChatGPT with a comprehensive review of its underlying technology, applications, and challenges. Moreover, we present an outlook on how ChatGPT might evolve to realize general-purpose AIGC (a.k.a. AI-generated content), which will be a significant milestone for the development of AGI.

Taeyeop Lee, Jonathan Tremblay, Valts Blukis et al.

Test-time adaptation methods have been gaining attention recently as a practical solution for addressing source-to-target domain gaps by gradually updating the model without requiring labels on the target data. In this paper, we propose a method of test-time adaptation for category-level object pose estimation called TTA-COPE. We design a pose ensemble approach with a self-training loss using pose-aware confidence. Unlike previous unsupervised domain adaptation methods for category-level object pose estimation, our approach processes the test data in a sequential, online manner, and it does not require access to the source domain at runtime. Extensive experimental results demonstrate that the proposed pose ensemble and the self-training loss improve category-level object pose performance during test time under both semi-supervised and unsupervised settings. Project page: https://taeyeop.com/ttacope

Inkyu Shin, Yi-Hsuan Tsai, Bingbing Zhuang et al.

Test-time adaptation approaches have recently emerged as a practical solution for handling domain shift without access to the source domain data. In this paper, we propose and explore a new multi-modal extension of test-time adaptation for 3D semantic segmentation. We find that directly applying existing methods usually results in performance instability at test time because multi-modal input is not considered jointly. To design a framework that can take full advantage of multi-modality, where each modality provides regularized self-supervisory signals to other modalities, we propose two complementary modules within and across the modalities. First, Intra-modal Pseudolabel Generation (Intra-PG) is introduced to obtain reliable pseudo labels within each modality by aggregating information from two models that are both pre-trained on source data but updated with target data at different paces. Second, Inter-modal Pseudo-label Refinement (Inter-PR) adaptively selects more reliable pseudo labels from different modalities based on a proposed consistency scheme. Experiments demonstrate that our regularized pseudo labels produce stable self-learning signals in numerous multi-modal test-time adaptation scenarios for 3D semantic segmentation. Visit our project website at https://www.nec-labs.com/~mas/MM-TTA.

Chenshuang Zhang, Chaoning Zhang, Sheng Zheng et al.

Generative AI has demonstrated impressive performance in various fields, among which speech synthesis is an interesting direction. With the diffusion model as the most popular generative model, numerous works have attempted two active tasks: text to speech and speech enhancement. This work conducts a survey on audio diffusion model, which is complementary to existing surveys that either lack the recent progress of diffusion-based speech synthesis or highlight an overall picture of applying diffusion model in multiple fields. Specifically, this work first briefly introduces the background of audio and diffusion model. As for the text-to-speech task, we divide the methods into three categories based on the stage where diffusion model is adopted: acoustic model, vocoder and end-to-end framework. Moreover, we categorize various speech enhancement tasks by either certain signals are removed or added into the input speech. Comparisons of experimental results and discussions are also covered in this survey.

Valts Blukis, Taeyeop Lee, Jonathan Tremblay et al.

We present a unified and compact scene representation for robotics, where each object in the scene is depicted by a latent code capturing geometry and appearance. This representation can be decoded for various tasks such as novel view rendering, 3D reconstruction (e.g. recovering depth, point clouds, or voxel maps), collision checking, and stable grasp prediction. We build our representation from a single RGB input image at test time by leveraging recent advances in Neural Radiance Fields (NeRF) that learn category-level priors on large multiview datasets, then fine-tune on novel objects from one or few views. We expand the NeRF model for additional grasp outputs and explore ways to leverage this representation for robotics. At test-time, we build the representation from a single RGB input image observing the scene from only one viewpoint. We find that the recovered representation allows rendering from novel views, including of occluded object parts, and also for predicting successful stable grasps. Grasp poses can be directly decoded from our latent representation with an implicit grasp decoder. We experimented in both simulation and real world and demonstrated the capability for robust robotic grasping using such compact representation. Website: https://nerfgrasp.github.io

Chaoning Zhang, Chenshuang Zhang, Junha Song et al.

Masked autoencoders are scalable vision learners, as the title of MAE \cite{he2022masked}, which suggests that self-supervised learning (SSL) in vision might undertake a similar trajectory as in NLP. Specifically, generative pretext tasks with the masked prediction (e.g., BERT) have become a de facto standard SSL practice in NLP. By contrast, early attempts at generative methods in vision have been buried by their discriminative counterparts (like contrastive learning); however, the success of mask image modeling has revived the masking autoencoder (often termed denoising autoencoder in the past). As a milestone to bridge the gap with BERT in NLP, masked autoencoder has attracted unprecedented attention for SSL in vision and beyond. This work conducts a comprehensive survey of masked autoencoders to shed insight on a promising direction of SSL. As the first to review SSL with masked autoencoders, this work focuses on its application in vision by discussing its historical developments, recent progress, and implications for diverse applications.

Junha Song, Jungsoo Lee, In So Kweon et al.

This paper presents a simple yet effective approach that improves continual test-time adaptation (TTA) in a memory-efficient manner. TTA may primarily be conducted on edge devices with limited memory, so reducing memory is crucial but has been overlooked in previous TTA studies. In addition, long-term adaptation often leads to catastrophic forgetting and error accumulation, which hinders applying TTA in real-world deployments. Our approach consists of two components to address these issues. First, we present lightweight meta networks that can adapt the frozen original networks to the target domain. This novel architecture minimizes memory consumption by decreasing the size of intermediate activations required for backpropagation. Second, our novel self-distilled regularization controls the output of the meta networks not to deviate significantly from the output of the frozen original networks, thereby preserving well-trained knowledge from the source domain. Without additional memory, this regularization prevents error accumulation and catastrophic forgetting, resulting in stable performance even in long-term test-time adaptation. We demonstrate that our simple yet effective strategy outperforms other state-of-the-art methods on various benchmarks for image classification and semantic segmentation tasks. Notably, our proposed method with ResNet-50 and WideResNet-40 takes 86% and 80% less memory than the recent state-of-the-art method, CoTTA.

Sanghyun Woo, Kwanyong Park, Seoung Wug Oh et al.

The tracking-by-detection paradigm today has become the dominant method for multi-object tracking and works by detecting objects in each frame and then performing data association across frames. However, its sequential frame-wise matching property fundamentally suffers from the intermediate interruptions in a video, such as object occlusions, fast camera movements, and abrupt light changes. Moreover, it typically overlooks temporal information beyond the two frames for matching. In this paper, we investigate an alternative by treating object association as clip-wise matching. Our new perspective views a single long video sequence as multiple short clips, and then the tracking is performed both within and between the clips. The benefits of this new approach are two folds. First, our method is robust to tracking error accumulation or propagation, as the video chunking allows bypassing the interrupted frames, and the short clip tracking avoids the conventional error-prone long-term track memory management. Second, the multiple frame information is aggregated during the clip-wise matching, resulting in a more accurate long-range track association than the current frame-wise matching. Given the state-of-the-art tracking-by-detection tracker, QDTrack, we showcase how the tracking performance improves with our new tracking formulation. We evaluate our proposals on two tracking benchmarks, TAO and MOT17 that have complementary characteristics and challenges each other.

Dawit Mureja Argaw, In So Kweon

Video frame interpolation (VFI) works generally predict intermediate frame(s) by first estimating the motion between inputs and then warping the inputs to the target time with the estimated motion. This approach, however, is not optimal when the temporal distance between the input sequence increases as existing motion estimation modules cannot effectively handle large motions. Hence, VFI works perform well for small frame gaps and perform poorly as the frame gap increases. In this work, we propose a novel framework to address this problem. We argue that when there is a large gap between inputs, instead of estimating imprecise motion that will eventually lead to inaccurate interpolation, we can safely propagate from one side of the input up to a reliable time frame using the other input as a reference. Then, the rest of the intermediate frames can be interpolated using standard approaches as the temporal gap is now narrowed. To this end, we propose a propagation network (PNet) by extending the classic feature-level forecasting with a novel motion-to-feature approach. To be thorough, we adopt a simple interpolation model along with PNet as our full model and design a simple procedure to train the full model in an end-to-end manner. Experimental results on several benchmark datasets confirm the effectiveness of our method for long-term VFI compared to state-of-the-art approaches.

Kwanyong Park, Sanghyun Woo, Seoung Wug Oh et al.

Recently, memory-based approaches show promising results on semi-supervised video object segmentation. These methods predict object masks frame-by-frame with the help of frequently updated memory of the previous mask. Different from this per-frame inference, we investigate an alternative perspective by treating video object segmentation as clip-wise mask propagation. In this per-clip inference scheme, we update the memory with an interval and simultaneously process a set of consecutive frames (i.e. clip) between the memory updates. The scheme provides two potential benefits: accuracy gain by clip-level optimization and efficiency gain by parallel computation of multiple frames. To this end, we propose a new method tailored for the per-clip inference. Specifically, we first introduce a clip-wise operation to refine the features based on intra-clip correlation. In addition, we employ a progressive matching mechanism for efficient information-passing within a clip. With the synergy of two modules and a newly proposed per-clip based training, our network achieves state-of-the-art performance on Youtube-VOS 2018/2019 val (84.6% and 84.6%) and DAVIS 2016/2017 val (91.9% and 86.1%). Furthermore, our model shows a great speed-accuracy trade-off with varying memory update intervals, which leads to huge flexibility.

Sanghyun Woo, Kwanyong Park, Seoung Wug Oh et al.

Scaling object taxonomies is one of the important steps toward a robust real-world deployment of recognition systems. We have faced remarkable progress in images since the introduction of the LVIS benchmark. To continue this success in videos, a new video benchmark, TAO, was recently presented. Given the recent encouraging results from both detection and tracking communities, we are interested in marrying those two advances and building a strong large vocabulary video tracker. However, supervisions in LVIS and TAO are inherently sparse or even missing, posing two new challenges for training the large vocabulary trackers. First, no tracking supervisions are in LVIS, which leads to inconsistent learning of detection (with LVIS and TAO) and tracking (only with TAO). Second, the detection supervisions in TAO are partial, which results in catastrophic forgetting of absent LVIS categories during video fine-tuning. To resolve these challenges, we present a simple but effective learning framework that takes full advantage of all available training data to learn detection and tracking while not losing any LVIS categories to recognize. With this new learning scheme, we show that consistent improvements of various large vocabulary trackers are capable, setting strong baseline results on the challenging TAO benchmarks.

Inkyu Shin, Dahun Kim, Qihang Yu et al.

Video Panoptic Segmentation (VPS) aims to achieve comprehensive pixel-level scene understanding by segmenting all pixels and associating objects in a video. Current solutions can be categorized into online and near-online approaches. Evolving over the time, each category has its own specialized designs, making it nontrivial to adapt models between different categories. To alleviate the discrepancy, in this work, we propose a unified approach for online and near-online VPS. The meta architecture of the proposed Video-kMaX consists of two components: within clip segmenter (for clip-level segmentation) and cross-clip associater (for association beyond clips). We propose clip-kMaX (clip k-means mask transformer) and HiLA-MB (Hierarchical Location-Aware Memory Buffer) to instantiate the segmenter and associater, respectively. Our general formulation includes the online scenario as a special case by adopting clip length of one. Without bells and whistles, Video-kMaX sets a new state-of-the-art on KITTI-STEP and VIPSeg for video panoptic segmentation, and VSPW for video semantic segmentation. Code will be made publicly available.

Dawit Mureja Argaw, Fabian Caba Heilbron, Joon-Young Lee et al.

Machine learning is transforming the video editing industry. Recent advances in computer vision have leveled-up video editing tasks such as intelligent reframing, rotoscoping, color grading, or applying digital makeups. However, most of the solutions have focused on video manipulation and VFX. This work introduces the Anatomy of Video Editing, a dataset, and benchmark, to foster research in AI-assisted video editing. Our benchmark suite focuses on video editing tasks, beyond visual effects, such as automatic footage organization and assisted video assembling. To enable research on these fronts, we annotate more than 1.5M tags, with relevant concepts to cinematography, from 196176 shots sampled from movie scenes. We establish competitive baseline methods and detailed analyses for each of the tasks. We hope our work sparks innovative research towards underexplored areas of AI-assisted video editing.

Ukcheol Shin, Kyunghyun Lee, In So Kweon

In this paper, we propose a multi-objective camera ISP framework that utilizes Deep Reinforcement Learning (DRL) and camera ISP toolbox that consist of network-based and conventional ISP tools. The proposed DRL-based camera ISP framework iteratively selects a proper tool from the toolbox and applies it to the image to maximize a given vision task-specific reward function. For this purpose, we implement total 51 ISP tools that include exposure correction, color-and-tone correction, white balance, sharpening, denoising, and the others. We also propose an efficient DRL network architecture that can extract the various aspects of an image and make a rigid mapping relationship between images and a large number of actions. Our proposed DRL-based ISP framework effectively improves the image quality according to each vision task such as RAW-to-RGB image restoration, 2D object detection, and monocular depth estimation.

Jae Won Cho, Dong-jin Kim, Hyeonggon Ryu et al.

The task of Visual Question Answering (VQA) is known to be plagued by the issue of VQA models exploiting biases within the dataset to make its final prediction. Various previous ensemble based debiasing methods have been proposed where an additional model is purposefully trained to be biased in order to train a robust target model. However, these methods compute the bias for a model simply from the label statistics of the training data or from single modal branches. In this work, in order to better learn the bias a target VQA model suffers from, we propose a generative method to train the bias model directly from the target model, called GenB. In particular, GenB employs a generative network to learn the bias in the target model through a combination of the adversarial objective and knowledge distillation. We then debias our target model with GenB as a bias model, and show through extensive experiments the effects of our method on various VQA bias datasets including VQA-CP2, VQA-CP1, GQA-OOD, and VQA-CE, and show state-of-the-art results with the LXMERT architecture on VQA-CP2.

Youngjoon Jang, Youngtaek Oh, Jae Won Cho et al.

The goal of this work is background-robust continuous sign language recognition. Most existing Continuous Sign Language Recognition (CSLR) benchmarks have fixed backgrounds and are filmed in studios with a static monochromatic background. However, signing is not limited only to studios in the real world. In order to analyze the robustness of CSLR models under background shifts, we first evaluate existing state-of-the-art CSLR models on diverse backgrounds. To synthesize the sign videos with a variety of backgrounds, we propose a pipeline to automatically generate a benchmark dataset utilizing existing CSLR benchmarks. Our newly constructed benchmark dataset consists of diverse scenes to simulate a real-world environment. We observe even the most recent CSLR method cannot recognize glosses well on our new dataset with changed backgrounds. In this regard, we also propose a simple yet effective training scheme including (1) background randomization and (2) feature disentanglement for CSLR models. The experimental results on our dataset demonstrate that our method generalizes well to other unseen background data with minimal additional training images.

Youngjoon Jang, Youngtaek Oh, Jae Won Cho et al.

The goal of this work is to develop self-sufficient framework for Continuous Sign Language Recognition (CSLR) that addresses key issues of sign language recognition. These include the need for complex multi-scale features such as hands, face, and mouth for understanding, and absence of frame-level annotations. To this end, we propose (1) Divide and Focus Convolution (DFConv) which extracts both manual and non-manual features without the need for additional networks or annotations, and (2) Dense Pseudo-Label Refinement (DPLR) which propagates non-spiky frame-level pseudo-labels by combining the ground truth gloss sequence labels with the predicted sequence. We demonstrate that our model achieves state-of-the-art performance among RGB-based methods on large-scale CSLR benchmarks, PHOENIX-2014 and PHOENIX-2014-T, while showing comparable results with better efficiency when compared to other approaches that use multi-modality or extra annotations.

Hyeonggon Ryu, Arda Senocak, In So Kweon et al.

The objective of this work is to explore the learning of visually grounded speech models (VGS) from multilingual perspective. Bilingual VGS models are generally trained with an equal number of spoken captions from both languages. However, in reality, there can be an imbalance among the languages for the available spoken captions. Our key contribution in this work is to leverage the power of a high-resource language in a bilingual visually grounded speech model to improve the performance of a low-resource language. We introduce two methods to distill the knowledge of high-resource language into low-resource languages: (1) incorporating a strong pre-trained high-resource language encoder and (2) using semantically similar spoken captions. Our experiments show that combining these two approaches effectively enables the low-resource language to surpass the performances of monolingual and bilingual counterparts for cross-modal retrieval tasks.

Fei Pan, Francois Rameau, Junsik Kim et al.

Training models dedicated to semantic segmentation requires a large amount of pixel-wise annotated data. Due to their costly nature, these annotations might not be available for the task at hand. To alleviate this problem, unsupervised domain adaptation approaches aim at aligning the feature distributions between the labeled source and the unlabeled target data. While these strategies lead to noticeable improvements, their effectiveness remains limited. To guide the domain adaptation task more efficiently, previous works attempted to include human interactions in this process under the form of sparse single-pixel annotations in the target data. In this work, we propose a new domain adaptation framework for semantic segmentation with annotated points via active selection. First, we conduct an unsupervised domain adaptation of the model; from this adaptation, we use an entropy-based uncertainty measurement for target points selection. Finally, to minimize the domain gap, we propose a domain adaptation framework utilizing these target points annotated by human annotators. Experimental results on benchmark datasets show the effectiveness of our methods against existing unsupervised domain adaptation approaches. The propose pipeline is generic and can be included as an extra module to existing domain adaptation strategies.

Dawit Mureja Argaw, Joon-Young Lee, Markus Woodson et al.

Learning computer vision models from (and for) movies has a long-standing history. While great progress has been attained, there is still a need for a pretrained multimodal model that can perform well in the ever-growing set of movie understanding tasks the community has been establishing. In this work, we introduce Long-range Multimodal Pretraining, a strategy, and a model that leverages movie data to train transferable multimodal and cross-modal encoders. Our key idea is to learn from all modalities in a movie by observing and extracting relationships over a long-range. After pretraining, we run ablation studies on the LVU benchmark and validate our modeling choices and the importance of learning from long-range time spans. Our model achieves state-of-the-art on several LVU tasks while being much more data efficient than previous works. Finally, we evaluate our model's transferability by setting a new state-of-the-art in five different benchmarks.

Joohyung Lee, Jieun Oh, Inkyu Shin et al.

Volumetric images from Magnetic Resonance Imaging (MRI) provide invaluable information in preoperative staging of rectal cancer. Above all, accurate preoperative discrimination between T2 and T3 stages is arguably both the most challenging and clinically significant task for rectal cancer treatment, as chemo-radiotherapy is usually recommended to patients with T3 (or greater) stage cancer. In this study, we present a volumetric convolutional neural network to accurately discriminate T2 from T3 stage rectal cancer with rectal MR volumes. Specifically, we propose 1) a custom ResNet-based volume encoder that models the inter-slice relationship with late fusion (i.e., 3D convolution at the last layer), 2) a bilinear computation that aggregates the resulting features from the encoder to create a volume-wise feature, and 3) a joint minimization of triplet loss and focal loss. With MR volumes of pathologically confirmed T2/T3 rectal cancer, we perform extensive experiments to compare various designs within the framework of residual learning. As a result, our network achieves an AUC of 0.831, which is higher than the reported accuracy of the professional radiologist groups. We believe this method can be extended to other volume analysis tasks

Dong-Jin Kim, Tae-Hyun Oh, Jinsoo Choi et al.

We present a novel data-efficient semi-supervised framework to improve the generalization of image captioning models. Constructing a large-scale labeled image captioning dataset is an expensive task in terms of labor, time, and cost. In contrast to manually annotating all the training samples, separately collecting uni-modal datasets is immensely easier, e.g., a large-scale image dataset and a sentence dataset. We leverage such massive unpaired image and caption data upon standard paired data by learning to associate them. To this end, our proposed semi-supervised learning method assigns pseudo-labels to unpaired samples in an adversarial learning fashion, where the joint distribution of image and caption is learned. Our method trains a captioner to learn from a paired data and to progressively associate unpaired data. This approach shows noticeable performance improvement even in challenging scenarios including out-of-task data (i.e., relational captioning, where the target task is different from the unpaired data) and web-crawled data. We also show that our proposed method is theoretically well-motivated and has a favorable global optimal property. Our extensive and comprehensive empirical results both on (1) image-based and (2) dense region-based captioning datasets followed by comprehensive analysis on the scarcely-paired COCO dataset demonstrate the consistent effectiveness of our semisupervised learning method with unpaired data compared to competing methods.

Sungsu Hur, Inkyu Shin, Kwanyong Park et al.

Universal Domain Adaptation aims to transfer the knowledge between the datasets by handling two shifts: domain-shift and category-shift. The main challenge is correctly distinguishing the unknown target samples while adapting the distribution of known class knowledge from source to target. Most existing methods approach this problem by first training the target adapted known classifier and then relying on the single threshold to distinguish unknown target samples. However, this simple threshold-based approach prevents the model from considering the underlying complexities existing between the known and unknown samples in the high-dimensional feature space. In this paper, we propose a new approach in which we use two sets of feature points, namely dual Classifiers for Prototypes and Reciprocals (CPR). Our key idea is to associate each prototype with corresponding known class features while pushing the reciprocals apart from these prototypes to locate them in the potential unknown feature space. The target samples are then classified as unknown if they fall near any reciprocals at test time. To successfully train our framework, we collect the partial, confident target samples that are classified as known or unknown through on our proposed multi-criteria selection. We then additionally apply the entropy loss regularization to them. For further adaptation, we also apply standard consistency regularization that matches the predictions of two different views of the input to make more compact target feature space. We evaluate our proposal, CPR, on three standard benchmarks and achieve comparable or new state-of-the-art results. We also provide extensive ablation experiments to verify our main design choices in our framework.

Fei Pan, Sungsu Hur, Seokju Lee et al.

Open compound domain adaptation (OCDA) considers the target domain as the compound of multiple unknown homogeneous subdomains. The goal of OCDA is to minimize the domain gap between the labeled source domain and the unlabeled compound target domain, which benefits the model generalization to the unseen domains. Current OCDA for semantic segmentation methods adopt manual domain separation and employ a single model to simultaneously adapt to all the target subdomains. However, adapting to a target subdomain might hinder the model from adapting to other dissimilar target subdomains, which leads to limited performance. In this work, we introduce a multi-teacher framework with bidirectional photometric mixing to separately adapt to every target subdomain. First, we present an automatic domain separation to find the optimal number of subdomains. On this basis, we propose a multi-teacher framework in which each teacher model uses bidirectional photometric mixing to adapt to one target subdomain. Furthermore, we conduct an adaptive distillation to learn a student model and apply consistency regularization to improve the student generalization. Experimental results on benchmark datasets show the efficacy of the proposed approach for both the compound domain and the open domains against existing state-of-the-art approaches.

Junha Song, Kwanyong Park, InKyu Shin et al.

Prior to the deployment of robotic systems, pre-training the deep-recognition models on all potential visual cases is infeasible in practice. Hence, test-time adaptation (TTA) allows the model to adapt itself to novel environments and improve its performance during test time (i.e., lifelong adaptation). Several works for TTA have shown promising adaptation performances in continuously changing environments. However, our investigation reveals that existing methods are vulnerable to dynamic distributional changes and often lead to overfitting of TTA models. To address this problem, this paper first presents a robust TTA framework with compound domain knowledge management. Our framework helps the TTA model to harvest the knowledge of multiple representative domains (i.e., compound domain) and conduct the TTA based on the compound domain knowledge. In addition, to prevent overfitting of the TTA model, we devise novel regularization which modulates the adaptation rates using domain-similarity between the source and the current target domain. With the synergy of the proposed framework and regularization, we achieve consistent performance improvements in diverse TTA scenarios, especially on dynamic domain shifts. We demonstrate the generality of proposals via extensive experiments including image classification on ImageNet-C and semantic segmentation on GTA5, C-driving, and corrupted Cityscapes datasets.

Dawit Mureja Argaw, Junsik Kim, In So Kweon

Existing video compression (VC) methods primarily aim to reduce the spatial and temporal redundancies between consecutive frames in a video while preserving its quality. In this regard, previous works have achieved remarkable results on videos acquired under specific settings such as instant (known) exposure time and shutter speed which often result in sharp videos. However, when these methods are evaluated on videos captured under different temporal priors, which lead to degradations like motion blur and low frame rate, they fail to maintain the quality of the contents. In this work, we tackle the VC problem in a general scenario where a given video can be blurry due to predefined camera settings or dynamics in the scene. By exploiting the natural trade-off between visual enhancement and data compression, we formulate VC as a min-max optimization problem and propose an effective framework and training strategy to tackle the problem. Extensive experimental results on several benchmark datasets confirm the effectiveness of our method compared to several state-of-the-art VC approaches.

Axi Niu, Kang Zhang, Joshua Tian Jin Tee et al.

It is well known the adversarial optimization of GAN-based image super-resolution (SR) methods makes the preceding SR model generate unpleasant and undesirable artifacts, leading to large distortion. We attribute the cause of such distortions to the poor calibration of the discriminator, which hampers its ability to provide meaningful feedback to the generator for learning high-quality images. To address this problem, we propose a simple but non-travel diffusion-style data augmentation scheme for current GAN-based SR methods, known as DifAugGAN. It involves adapting the diffusion process in generative diffusion models for improving the calibration of the discriminator during training motivated by the successes of data augmentation schemes in the field to achieve good calibration. Our DifAugGAN can be a Plug-and-Play strategy for current GAN-based SISR methods to improve the calibration of the discriminator and thus improve SR performance. Extensive experimental evaluations demonstrate the superiority of DifAugGAN over state-of-the-art GAN-based SISR methods across both synthetic and real-world datasets, showcasing notable advancements in both qualitative and quantitative results.

Chenshuang Zhang, Fei Pan, Junmo Kim et al.

We establish rigorous benchmarks for visual perception robustness. Synthetic images such as ImageNet-C, ImageNet-9, and Stylized ImageNet provide specific type of evaluation over synthetic corruptions, backgrounds, and textures, yet those robustness benchmarks are restricted in specified variations and have low synthetic quality. In this work, we introduce generative model as a data source for synthesizing hard images that benchmark deep models' robustness. Leveraging diffusion models, we are able to generate images with more diversified backgrounds, textures, and materials than any prior work, where we term this benchmark as ImageNet-D. Experimental results show that ImageNet-D results in a significant accuracy drop to a range of vision models, from the standard ResNet visual classifier to the latest foundation models like CLIP and MiniGPT-4, significantly reducing their accuracy by up to 60\%. Our work suggests that diffusion models can be an effective source to test vision models. The code and dataset are available at https://github.com/chenshuang-zhang/imagenet_d.

Myungchul Kim, Kwanyong Park, Junmo Kim et al.

We introduce ARGOS, the first benchmark and framework that reformulates multi-camera person search as an interactive reasoning problem requiring an agent to plan, question, and eliminate candidates under information asymmetry. An ARGOS agent receives a vague witness statement and must decide what to ask, when to invoke spatial or temporal tools, and how to interpret ambiguous responses, all within a limited turn budget. Reasoning is grounded in a Spatio-Temporal Topology Graph (STTG) encoding camera connectivity and empirically validated transition times. The benchmark comprises 2,691 tasks across 14 real-world scenarios in three progressive tracks: semantic perception (Who), spatial reasoning (Where), and temporal reasoning (When). Experiments with four LLM backbones show the benchmark is far from solved (best TWS: 0.383 on Track 2, 0.590 on Track 3), and ablations confirm that removing domain-specific tools drops accuracy by up to 49.6 percentage points.

Minjun Kang, Inkyu Shin, Taeyeop Lee et al.

Novel view synthesis requires strong 3D geometric consistency and the ability to generate visually coherent images across diverse viewpoints. While recent camera-controlled video diffusion models show promising results, they often suffer from geometric distortions and limited camera controllability. To overcome these challenges, we introduce GeoNVS, a geometry-grounded novel-view synthesizer that enhances both geometric fidelity and camera controllability through explicit 3D geometric guidance. Our key innovation is the Gaussian Splat Feature Adapter (GS-Adapter), which lifts input-view diffusion features into 3D Gaussian representations, renders geometry-constrained novel-view features, and adaptively fuses them with diffusion features to correct geometrically inconsistent representations. Unlike prior methods that inject geometry at the input level, GS-Adapter operates in feature space, avoiding view-dependent color noise that degrades structural consistency. Its plug-and-play design enables zero-shot compatibility with diverse feed-forward geometry models without additional training, and can be adapted to other video diffusion backbones. Experiments across 9 scenes and 18 settings demonstrate state-of-the-art performance, achieving 11.3% and 14.9% improvements over SEVA and CameraCtrl, with up to 2x reduction in translation error and 7x in Chamfer Distance.

Chenshuang Zhang, Kang Zhang, Joon Son Chung et al.

Distinguishing visually similar objects by their motion remains a critical challenge in computer vision. Although supervised trackers show promise, contemporary self-supervised trackers struggle when visual cues become ambiguous, limiting their scalability and generalization without extensive labeled data. We find that pre-trained video diffusion models inherently learn motion representations suitable for tracking without task-specific training. This ability arises because their denoising process isolates motion in early, high-noise stages, distinct from later appearance refinement. Capitalizing on this discovery, our self-supervised tracker significantly improves performance in distinguishing visually similar objects, an underexplored failure point for existing methods. Our method achieves up to a 6-point improvement over recent self-supervised approaches on established benchmarks and our newly introduced tests focused on tracking visually similar items. Visualizations confirm that these diffusion-derived motion representations enable robust tracking of even identical objects across challenging viewpoint changes and deformations.

Youngtaek Oh, Pyunghwan Ahn, Jinhyung Kim et al.

Vision and language models (VLMs) such as CLIP have showcased remarkable zero-shot recognition abilities yet face challenges in visio-linguistic compositionality, particularly in linguistic comprehension and fine-grained image-text alignment. This paper explores the intricate relationship between compositionality and recognition -- two pivotal aspects of VLM capability. We conduct a comprehensive evaluation of existing VLMs, covering both pre-training approaches aimed at recognition and the fine-tuning methods designed to improve compositionality. Our evaluation employs 12 benchmarks for compositionality, along with 21 zero-shot classification and two retrieval benchmarks for recognition. In our analysis from 274 CLIP model checkpoints, we reveal patterns and trade-offs that emerge between compositional understanding and recognition accuracy. Ultimately, this necessitates strategic efforts towards developing models that improve both capabilities, as well as the meticulous formulation of benchmarks for compositionality. We open our evaluation framework at https://github.com/ytaek-oh/vl_compo.

Chaoning Zhang, Philipp Benz, Adil Karjauv et al.

Existing works have identified the limitation of top-$1$ attack success rate (ASR) as a metric to evaluate the attack strength but exclusively investigated it in the white-box setting, while our work extends it to a more practical black-box setting: transferable attack. It is widely reported that stronger I-FGSM transfers worse than simple FGSM, leading to a popular belief that transferability is at odds with the white-box attack strength. Our work challenges this belief with empirical finding that stronger attack actually transfers better for the general top-$k$ ASR indicated by the interest class rank (ICR) after attack. For increasing the attack strength, with an intuitive interpretation of the logit gradient from the geometric perspective, we identify that the weakness of the commonly used losses lie in prioritizing the speed to fool the network instead of maximizing its strength. To this end, we propose a new normalized CE loss that guides the logit to be updated in the direction of implicitly maximizing its rank distance from the ground-truth class. Extensive results in various settings have verified that our proposed new loss is simple yet effective for top-$k$ attack. Code is available at: \url{https://bit.ly/3uCiomP}

Chaoning Zhang, Kang Zhang, Trung X. Pham et al.

Contrastive learning (CL) is widely known to require many negative samples, 65536 in MoCo for instance, for which the performance of a dictionary-free framework is often inferior because the negative sample size (NSS) is limited by its mini-batch size (MBS). To decouple the NSS from the MBS, a dynamic dictionary has been adopted in a large volume of CL frameworks, among which arguably the most popular one is MoCo family. In essence, MoCo adopts a momentum-based queue dictionary, for which we perform a fine-grained analysis of its size and consistency. We point out that InfoNCE loss used in MoCo implicitly attract anchors to their corresponding positive sample with various strength of penalties and identify such inter-anchor hardness-awareness property as a major reason for the necessity of a large dictionary. Our findings motivate us to simplify MoCo v2 via the removal of its dictionary as well as momentum. Based on an InfoNCE with the proposed dual temperature, our simplified frameworks, SimMoCo and SimCo, outperform MoCo v2 by a visible margin. Moreover, our work bridges the gap between CL and non-CL frameworks, contributing to a more unified understanding of these two mainstream frameworks in SSL. Code is available at: https://bit.ly/3LkQbaT.

Antyanta Bangunharcana, Jae Won Cho, Seokju Lee et al.

Volumetric deep learning approach towards stereo matching aggregates a cost volume computed from input left and right images using 3D convolutions. Recent works showed that utilization of extracted image features and a spatially varying cost volume aggregation complements 3D convolutions. However, existing methods with spatially varying operations are complex, cost considerable computation time, and cause memory consumption to increase. In this work, we construct Guided Cost volume Excitation (GCE) and show that simple channel excitation of cost volume guided by image can improve performance considerably. Moreover, we propose a novel method of using top-k selection prior to soft-argmin disparity regression for computing the final disparity estimate. Combining our novel contributions, we present an end-to-end network that we call Correlate-and-Excite (CoEx). Extensive experiments of our model on the SceneFlow, KITTI 2012, and KITTI 2015 datasets demonstrate the effectiveness and efficiency of our model and show that our model outperforms other speed-based algorithms while also being competitive to other state-of-the-art algorithms. Codes will be made available at https://github.com/antabangun/coex.

Seokju Lee, Sunghoon Im, Stephen Lin et al.

We present an end-to-end joint training framework that explicitly models 6-DoF motion of multiple dynamic objects, ego-motion and depth in a monocular camera setup without supervision. Our technical contributions are three-fold. First, we highlight the fundamental difference between inverse and forward projection while modeling the individual motion of each rigid object, and propose a geometrically correct projection pipeline using a neural forward projection module. Second, we design a unified instance-aware photometric and geometric consistency loss that holistically imposes self-supervisory signals for every background and object region. Lastly, we introduce a general-purpose auto-annotation scheme using any off-the-shelf instance segmentation and optical flow models to produce video instance segmentation maps that will be utilized as input to our training pipeline. These proposed elements are validated in a detailed ablation study. Through extensive experiments conducted on the KITTI and Cityscapes dataset, our framework is shown to outperform the state-of-the-art depth and motion estimation methods. Our code, dataset, and models are available at https://github.com/SeokjuLee/Insta-DM .

Fei Pan, Inkyu Shin, Francois Rameau et al.

Convolutional neural network-based approaches have achieved remarkable progress in semantic segmentation. However, these approaches heavily rely on annotated data which are labor intensive. To cope with this limitation, automatically annotated data generated from graphic engines are used to train segmentation models. However, the models trained from synthetic data are difficult to transfer to real images. To tackle this issue, previous works have considered directly adapting models from the source data to the unlabeled target data (to reduce the inter-domain gap). Nonetheless, these techniques do not consider the large distribution gap among the target data itself (intra-domain gap). In this work, we propose a two-step self-supervised domain adaptation approach to minimize the inter-domain and intra-domain gap together. First, we conduct the inter-domain adaptation of the model; from this adaptation, we separate the target domain into an easy and hard split using an entropy-based ranking function. Finally, to decrease the intra-domain gap, we propose to employ a self-supervised adaptation technique from the easy to the hard split. Experimental results on numerous benchmark datasets highlight the effectiveness of our method against existing state-of-the-art approaches. The source code is available at https://github.com/feipan664/IntraDA.git.

Seokju Lee, Sunghoon Im, Stephen Lin et al.

We present an end-to-end joint training framework that explicitly models 6-DoF motion of multiple dynamic objects, ego-motion and depth in a monocular camera setup without supervision. Our technical contributions are three-fold. First, we propose a differentiable forward rigid projection module that plays a key role in our instance-wise depth and motion learning. Second, we design an instance-wise photometric and geometric consistency loss that effectively decomposes background and moving object regions. Lastly, we introduce a new auto-annotation scheme to produce video instance segmentation maps that will be utilized as input to our training pipeline. These proposed elements are validated in a detailed ablation study. Through extensive experiments conducted on the KITTI dataset, our framework is shown to outperform the state-of-the-art depth and motion estimation methods. Our code and dataset will be available at https://github.com/SeokjuLee/Insta-DM.

Taeyeop Lee, Bowen Wen, Minjun Kang et al.

We introduce Any6D, a model-free framework for 6D object pose estimation that requires only a single RGB-D anchor image to estimate both the 6D pose and size of unknown objects in novel scenes. Unlike existing methods that rely on textured 3D models or multiple viewpoints, Any6D leverages a joint object alignment process to enhance 2D-3D alignment and metric scale estimation for improved pose accuracy. Our approach integrates a render-and-compare strategy to generate and refine pose hypotheses, enabling robust performance in scenarios with occlusions, non-overlapping views, diverse lighting conditions, and large cross-environment variations. We evaluate our method on five challenging datasets: REAL275, Toyota-Light, HO3D, YCBINEOAT, and LM-O, demonstrating its effectiveness in significantly outperforming state-of-the-art methods for novel object pose estimation. Project page: https://taeyeop.com/any6d