Kwanghoon Sohn

Jungin Park, Jiyoung Lee, Kwanghoon Sohn

This study introduces an intriguing phenomenon in Video LLMs: rather than merely translating frames into textual embeddings, Video LLMs establish a continuous manifold, token interface, allowing visual tokens to operate as standalone entities within the architecture. Exploiting this discovery, we propose V-LynX, a scalable framework that integrates novel modalities into Video LLMs by repurposing the internalized interface. Departing from conventional paradigms that necessitate heavy modality-specific encoders or paired supervision, V-LynX employs a lightweight auxiliary pathway in parallel with the frozen vision encoder. Our method integrates new sensory inputs with intrinsic video priors by aligning both attention responses and statistical distributions using unpaired unimodal data sets. This ensures manifold compatibility while preserving the integrity of the Video LLMs. Extensive benchmarks demonstrate that V-LynX achieves SOTA and efficiency across audio-visual QA, 3D reasoning, high-frame-rate, and multi-view video understanding. The code is available at https://github.com/park-jungin/lynx.

Tuan N. Tang, Kwonyoung Kim, Kwanghoon Sohn

Temporal Action Localization (TAL) is a challenging task in video understanding that aims to identify and localize actions within a video sequence. Recent studies have emphasized the importance of applying long-term temporal context modeling (TCM) blocks to the extracted video clip features such as employing complex self-attention mechanisms. In this paper, we present the simplest method ever to address this task and argue that the extracted video clip features are already informative to achieve outstanding performance without sophisticated architectures. To this end, we introduce TemporalMaxer, which minimizes long-term temporal context modeling while maximizing information from the extracted video clip features with a basic, parameter-free, and local region operating max-pooling block. Picking out only the most critical information for adjacent and local clip embeddings, this block results in a more efficient TAL model. We demonstrate that TemporalMaxer outperforms other state-of-the-art methods that utilize long-term TCM such as self-attention on various TAL datasets while requiring significantly fewer parameters and computational resources. The code for our approach is publicly available at https://github.com/TuanTNG/TemporalMaxer

Hanjae Kim, Jiyoung Lee, Seongheon Park et al.

Compositional zero-shot learning (CZSL) aims to recognize unseen compositions with prior knowledge of known primitives (attribute and object). Previous works for CZSL often suffer from grasping the contextuality between attribute and object, as well as the discriminability of visual features, and the long-tailed distribution of real-world compositional data. We propose a simple and scalable framework called Composition Transformer (CoT) to address these issues. CoT employs object and attribute experts in distinctive manners to generate representative embeddings, using the visual network hierarchically. The object expert extracts representative object embeddings from the final layer in a bottom-up manner, while the attribute expert makes attribute embeddings in a top-down manner with a proposed object-guided attention module that models contextuality explicitly. To remedy biased prediction caused by imbalanced data distribution, we develop a simple minority attribute augmentation (MAA) that synthesizes virtual samples by mixing two images and oversampling minority attribute classes. Our method achieves SoTA performance on several benchmarks, including MIT-States, C-GQA, and VAW-CZSL. We also demonstrate the effectiveness of CoT in improving visual discrimination and addressing the model bias from the imbalanced data distribution. The code is available at https://github.com/HanjaeKim98/CoT.

Jungin Park, Jiyoung Lee, Kwanghoon Sohn

Model merging aims to consolidate multiple task-specific models fine-tuned on different datasets into a unified architecture that performs cross-domain proficiency. Current data-free model merging methods often struggle to scale as they rely on simple parameter-level heuristics that ignore inter-layer dependencies and non-uniform distribution of expertise. This work proposes SA-Merging, which is built upon connectivity-based saliency formulations from structural pruning (e.g., SynFlow) and extends them to the data-free model merging setting. We define a saliency score over task vectors relative to a shared base model, and further introduce merge-aware modulation that incorporates agreement across experts to mitigate task interference. Based on this formulation, an iterative saliency-aware merging procedure progressively removes non-informative updates while preserving end-to-end connectivity. Furthermore, we extend SA-Merging to introduce rank-wise saliency decomposition for LoRAs without compromising their structural integrity. Extensive experiments on vision and language tasks demonstrate the effectiveness of our saliency-based approach, further reducing the gap between data-free and test-time adaptation methods.

Tuan N. Tang, Jungin Park, Kwonyoung Kim et al.

Online Temporal Action Localization (On-TAL) aims to immediately provide action instances from untrimmed streaming videos. The model is not allowed to utilize future frames and any processing techniques to modify past predictions, making On-TAL much more challenging. In this paper, we propose a simple yet effective framework, termed SimOn, that learns to predict action instances using the popular Transformer architecture in an end-to-end manner. Specifically, the model takes the current frame feature as a query and a set of past context information as keys and values of the Transformer. Different from the prior work that uses a set of outputs of the model as past contexts, we leverage the past visual context and the learnable context embedding for the current query. Experimental results on the THUMOS14 and ActivityNet1.3 datasets show that our model remarkably outperforms the previous methods, achieving a new state-of-the-art On-TAL performance. In addition, the evaluation for Online Detection of Action Start (ODAS) demonstrates the effectiveness and robustness of our method in the online setting. The code is available at https://github.com/TuanTNG/SimOn

Jinhyun Jang, Jungin Park, Jin Kim et al.

Recent DETR-based video grounding models have made the model directly predict moment timestamps without any hand-crafted components, such as a pre-defined proposal or non-maximum suppression, by learning moment queries. However, their input-agnostic moment queries inevitably overlook an intrinsic temporal structure of a video, providing limited positional information. In this paper, we formulate an event-aware dynamic moment query to enable the model to take the input-specific content and positional information of the video into account. To this end, we present two levels of reasoning: 1) Event reasoning that captures distinctive event units constituting a given video using a slot attention mechanism; and 2) moment reasoning that fuses the moment queries with a given sentence through a gated fusion transformer layer and learns interactions between the moment queries and video-sentence representations to predict moment timestamps. Extensive experiments demonstrate the effectiveness and efficiency of the event-aware dynamic moment queries, outperforming state-of-the-art approaches on several video grounding benchmarks.

Jin Kim, Jiyoung Lee, Jungin Park et al.

The rise of deep neural networks has led to several breakthroughs for semantic segmentation. In spite of this, a model trained on source domain often fails to work properly in new challenging domains, that is directly concerned with the generalization capability of the model. In this paper, we present a novel memory-guided domain generalization method for semantic segmentation based on meta-learning framework. Especially, our method abstracts the conceptual knowledge of semantic classes into categorical memory which is constant beyond the domains. Upon the meta-learning concept, we repeatedly train memory-guided networks and simulate virtual test to 1) learn how to memorize a domain-agnostic and distinct information of classes and 2) offer an externally settled memory as a class-guidance to reduce the ambiguity of representation in the test data of arbitrary unseen domain. To this end, we also propose memory divergence and feature cohesion losses, which encourage to learn memory reading and update processes for category-aware domain generalization. Extensive experiments for semantic segmentation demonstrate the superior generalization capability of our method over state-of-the-art works on various benchmarks.

Jungin Park, Jiyoung Lee, Kwanghoon Sohn

In this paper, we efficiently transfer the surpassing representation power of the vision foundation models, such as ViT and Swin, for video understanding with only a few trainable parameters. Previous adaptation methods have simultaneously considered spatial and temporal modeling with a unified learnable module but still suffered from fully leveraging the representative capabilities of image transformers. We argue that the popular dual-path (two-stream) architecture in video models can mitigate this problem. We propose a novel DualPath adaptation separated into spatial and temporal adaptation paths, where a lightweight bottleneck adapter is employed in each transformer block. Especially for temporal dynamic modeling, we incorporate consecutive frames into a grid-like frameset to precisely imitate vision transformers' capability that extrapolates relationships between tokens. In addition, we extensively investigate the multiple baselines from a unified perspective in video understanding and compare them with DualPath. Experimental results on four action recognition benchmarks prove that pretrained image transformers with DualPath can be effectively generalized beyond the data domain.

Jungin Park, Jiyoung Lee, Ig-Jae Kim et al.

This paper presents Probabilistic Video Contrastive Learning, a self-supervised representation learning method that bridges contrastive learning with probabilistic representation. We hypothesize that the clips composing the video have different distributions in short-term duration, but can represent the complicated and sophisticated video distribution through combination in a common embedding space. Thus, the proposed method represents video clips as normal distributions and combines them into a Mixture of Gaussians to model the whole video distribution. By sampling embeddings from the whole video distribution, we can circumvent the careful sampling strategy or transformations to generate augmented views of the clips, unlike previous deterministic methods that have mainly focused on such sample generation strategies for contrastive learning. We further propose a stochastic contrastive loss to learn proper video distributions and handle the inherent uncertainty from the nature of the raw video. Experimental results verify that our probabilistic embedding stands as a state-of-the-art video representation learning for action recognition and video retrieval on the most popular benchmarks, including UCF101 and HMDB51.

Minsu Kim, Seungryong Kim, JungIn Park et al.

Modern data augmentation using a mixture-based technique can regularize the models from overfitting to the training data in various computer vision applications, but a proper data augmentation technique tailored for the part-based Visible-Infrared person Re-IDentification (VI-ReID) models remains unexplored. In this paper, we present a novel data augmentation technique, dubbed PartMix, that synthesizes the augmented samples by mixing the part descriptors across the modalities to improve the performance of part-based VI-ReID models. Especially, we synthesize the positive and negative samples within the same and across different identities and regularize the backbone model through contrastive learning. In addition, we also present an entropy-based mining strategy to weaken the adverse impact of unreliable positive and negative samples. When incorporated into existing part-based VI-ReID model, PartMix consistently boosts the performance. We conduct experiments to demonstrate the effectiveness of our PartMix over the existing VI-ReID methods and provide ablation studies.

Dahye Kim, Jungin Park, Jiyoung Lee et al.

Given an untrimmed video and a language query depicting a specific temporal moment in the video, video grounding aims to localize the time interval by understanding the text and video simultaneously. One of the most challenging issues is an extremely time- and cost-consuming annotation collection, including video captions in a natural language form and their corresponding temporal regions. In this paper, we present a simple yet novel training framework for video grounding in the zero-shot setting, which learns a network with only video data without any annotation. Inspired by the recent language-free paradigm, i.e. training without language data, we train the network without compelling the generation of fake (pseudo) text queries into a natural language form. Specifically, we propose a method for learning a video grounding model by selecting a temporal interval as a hypothetical correct answer and considering the visual feature selected by our method in the interval as a language feature, with the help of the well-aligned visual-language space of CLIP. Extensive experiments demonstrate the prominence of our language-free training framework, outperforming the existing zero-shot video grounding method and even several weakly-supervised approaches with large margins on two standard datasets.

Hyeongjun Kwon, Taeyong Song, Somi Jeong et al.

Recent progress in deterministic prompt learning has become a promising alternative to various downstream vision tasks, enabling models to learn powerful visual representations with the help of pre-trained vision-language models. However, this approach results in limited performance for dense prediction tasks that require handling more complex and diverse objects, since a single and deterministic description cannot sufficiently represent the entire image. In this paper, we present a novel probabilistic prompt learning to fully exploit the vision-language knowledge in dense prediction tasks. First, we introduce learnable class-agnostic attribute prompts to describe universal attributes across the object class. The attributes are combined with class information and visual-context knowledge to define the class-specific textual distribution. Text representations are sampled and used to guide the dense prediction task using the probabilistic pixel-text matching loss, enhancing the stability and generalization capability of the proposed method. Extensive experiments on different dense prediction tasks and ablation studies demonstrate the effectiveness of our proposed method.

Ilhoon Yoon, Hyeongjun Kwon, Jin Kim et al.

Source-Free domain adaptive Object Detection (SFOD) is a promising strategy for deploying trained detectors to new, unlabeled domains without accessing source data, addressing significant concerns around data privacy and efficiency. Most SFOD methods leverage a Mean-Teacher (MT) self-training paradigm relying heavily on High-confidence Pseudo Labels (HPL). However, these HPL often overlook small instances that undergo significant appearance changes with domain shifts. Additionally, HPL ignore instances with low confidence due to the scarcity of training samples, resulting in biased adaptation toward familiar instances from the source domain. To address this limitation, we introduce the Low-confidence Pseudo Label Distillation (LPLD) loss within the Mean-Teacher based SFOD framework. This novel approach is designed to leverage the proposals from Region Proposal Network (RPN), which potentially encompasses hard-to-detect objects in unfamiliar domains. Initially, we extract HPL using a standard pseudo-labeling technique and mine a set of Low-confidence Pseudo Labels (LPL) from proposals generated by RPN, leaving those that do not overlap significantly with HPL. These LPL are further refined by leveraging class-relation information and reducing the effect of inherent noise for the LPLD loss calculation. Furthermore, we use feature distance to adaptively weight the LPLD loss to focus on LPL containing a larger foreground area. Our method outperforms previous SFOD methods on four cross-domain object detection benchmarks. Extensive experiments demonstrate that our LPLD loss leads to effective adaptation by reducing false negatives and facilitating the use of domain-invariant knowledge from the source model. Code is available at https://github.com/junia3/LPLD.

Kwonyoung Kim, Jungin Park, Jiyoung Lee et al.

Online stereo adaptation tackles the domain shift problem, caused by different environments between synthetic (training) and real (test) datasets, to promptly adapt stereo models in dynamic real-world applications such as autonomous driving. However, previous methods often fail to counteract particular regions related to dynamic objects with more severe environmental changes. To mitigate this issue, we propose to incorporate an auxiliary point-selective network into a meta-learning framework, called PointFix, to provide a robust initialization of stereo models for online stereo adaptation. In a nutshell, our auxiliary network learns to fix local variants intensively by effectively back-propagating local information through the meta-gradient for the robust initialization of the baseline model. This network is model-agnostic, so can be used in any kind of architectures in a plug-and-play manner. We conduct extensive experiments to verify the effectiveness of our method under three adaptation settings such as short-, mid-, and long-term sequences. Experimental results show that the proper initialization of the base stereo model by the auxiliary network enables our learning paradigm to achieve state-of-the-art performance at inference.

Jinhyun Jang, Taeyong Song, Kwanghoon Sohn

Aerial-to-ground image synthesis is an emerging and challenging problem that aims to synthesize a ground image from an aerial image. Due to the highly different layout and object representation between the aerial and ground images, existing approaches usually fail to transfer the components of the aerial scene into the ground scene. In this paper, we propose a novel framework to explore the challenges by imposing enhanced structural alignment and semantic awareness. We introduce a novel semantic-attentive feature transformation module that allows to reconstruct the complex geographic structures by aligning the aerial feature to the ground layout. Furthermore, we propose semantic-aware loss functions by leveraging a pre-trained segmentation network. The network is enforced to synthesize realistic objects across various classes by separately calculating losses for different classes and balancing them. Extensive experiments including comparisons with previous methods and ablation studies show the effectiveness of the proposed framework both qualitatively and quantitatively.

Junyoung Park, Jin Kim, Hyeongjun Kwon et al.

Given the inevitability of domain shifts during inference in real-world applications, test-time adaptation (TTA) is essential for model adaptation after deployment. However, the real-world scenario of continuously changing target distributions presents challenges including catastrophic forgetting and error accumulation. Existing TTA methods for non-stationary domain shifts, while effective, incur excessive computational load, making them impractical for on-device settings. In this paper, we introduce a layer-wise auto-weighting algorithm for continual and gradual TTA that autonomously identifies layers for preservation or concentrated adaptation. By leveraging the Fisher Information Matrix (FIM), we first design the learning weight to selectively focus on layers associated with log-likelihood changes while preserving unrelated ones. Then, we further propose an exponential min-max scaler to make certain layers nearly frozen while mitigating outliers. This minimizes forgetting and error accumulation, leading to efficient adaptation to non-stationary target distribution. Experiments on CIFAR-10C, CIFAR-100C, and ImageNet-C show our method outperforms conventional continual and gradual TTA approaches while significantly reducing computational load, highlighting the importance of FIM-based learning weight in adapting to continuously or gradually shifting target domains.

Jihyun Kim, Changjae Oh, Hoseok Do et al.

We present a new multi-modal face image generation method that converts a text prompt and a visual input, such as a semantic mask or scribble map, into a photo-realistic face image. To do this, we combine the strengths of Generative Adversarial networks (GANs) and diffusion models (DMs) by employing the multi-modal features in the DM into the latent space of the pre-trained GANs. We present a simple mapping and a style modulation network to link two models and convert meaningful representations in feature maps and attention maps into latent codes. With GAN inversion, the estimated latent codes can be used to generate 2D or 3D-aware facial images. We further present a multi-step training strategy that reflects textual and structural representations into the generated image. Our proposed network produces realistic 2D, multi-view, and stylized face images, which align well with inputs. We validate our method by using pre-trained 2D and 3D GANs, and our results outperform existing methods. Our project page is available at https://github.com/1211sh/Diffusion-driven_GAN-Inversion/.

Jungin Park, Jiyoung Lee, Kwanghoon Sohn

View-invariant representation learning from egocentric (first-person, ego) and exocentric (third-person, exo) videos is a promising approach toward generalizing video understanding systems across multiple viewpoints. However, this area has been underexplored due to the substantial differences in perspective, motion patterns, and context between ego and exo views. In this paper, we propose a novel masked ego-exo modeling that promotes both causal temporal dynamics and cross-view alignment, called Bootstrap Your Own Views (BYOV), for fine-grained view-invariant video representation learning from unpaired ego-exo videos. We highlight the importance of capturing the compositional nature of human actions as a basis for robust cross-view understanding. Specifically, self-view masking and cross-view masking predictions are designed to learn view-invariant and powerful representations concurrently. Experimental results demonstrate that our BYOV significantly surpasses existing approaches with notable gains across all metrics in four downstream ego-exo video tasks. The code is available at https://github.com/park-jungin/byov.

Jungin Park, Jiyoung Lee, Kwanghoon Sohn

Video summarization aims to select keyframes that are visually diverse and can represent the whole story of a given video. Previous approaches have focused on global interlinkability between frames in a video by temporal modeling. However, fine-grained visual entities, such as objects, are also highly related to the main content of the video. Moreover, language-guided video summarization, which has recently been studied, requires a comprehensive linguistic understanding of complex real-world videos. To consider how all the objects are semantically related to each other, this paper regards video summarization as a language-guided spatiotemporal graph modeling problem. We present recursive spatiotemporal graph networks, called VideoGraph, which formulate the objects and frames as nodes of the spatial and temporal graphs, respectively. The nodes in each graph are connected and aggregated with graph edges, representing the semantic relationships between the nodes. To prevent the edges from being configured with visual similarity, we incorporate language queries derived from the video into the graph node representations, enabling them to contain semantic knowledge. In addition, we adopt a recursive strategy to refine initial graphs and correctly classify each frame node as a keyframe. In our experiments, VideoGraph achieves state-of-the-art performance on several benchmarks for generic and query-focused video summarization in both supervised and unsupervised manners. The code is available at https://github.com/park-jungin/videograph.

Hyeongjun Kwon, Somi Jeong, Sunok Kim et al.

We address the problem of few-shot semantic segmentation (FSS), which aims to segment novel class objects in a target image with a few annotated samples. Though recent advances have been made by incorporating prototype-based metric learning, existing methods still show limited performance under extreme intra-class object variations and semantically similar inter-class objects due to their poor feature representation. To tackle this problem, we propose a dual prototypical contrastive learning approach tailored to the FSS task to capture the representative semanticfeatures effectively. The main idea is to encourage the prototypes more discriminative by increasing inter-class distance while reducing intra-class distance in prototype feature space. To this end, we first present a class-specific contrastive loss with a dynamic prototype dictionary that stores the class-aware prototypes during training, thus enabling the same class prototypes similar and the different class prototypes to be dissimilar. Furthermore, we introduce a class-agnostic contrastive loss to enhance the generalization ability to unseen classes by compressing the feature distribution of semantic class within each episode. We demonstrate that the proposed dual prototypical contrastive learning approach outperforms state-of-the-art FSS methods on PASCAL-5i and COCO-20i datasets. The code is available at:https://github.com/kwonjunn01/DPCL1.

Jungin Park, Jiyoung Lee, Kwanghoon Sohn

This paper introduces VLAP, a novel approach that bridges pretrained vision models and large language models (LLMs) to make frozen LLMs understand the visual world. VLAP transforms the embedding space of pretrained vision models into the LLMs' word embedding space using a single linear layer for efficient and general-purpose visual and language understanding. Specifically, we harness well-established word embeddings to bridge two modality embedding spaces. The visual and text representations are simultaneously assigned to a set of word embeddings within pretrained LLMs by formulating the assigning procedure as an optimal transport problem. We predict the assignment of one modality from the representation of another modality data, enforcing consistent assignments for paired multimodal data. This allows vision and language representations to contain the same information, grounding the frozen LLMs' word embedding space in visual data. Moreover, a robust semantic taxonomy of LLMs can be preserved with visual data since the LLMs interpret and reason linguistic information from correlations between word embeddings. Experimental results show that VLAP achieves substantial improvements over the previous linear transformation-based approaches across a range of vision-language tasks, including image captioning, visual question answering, and cross-modal retrieval. We also demonstrate the learned visual representations hold a semantic taxonomy of LLMs, making visual semantic arithmetic possible.

Hyeongjun Kwon, Jinhyun Jang, Jin Kim et al.

Visual scenes are naturally organized in a hierarchy, where a coarse semantic is recursively comprised of several fine details. Exploring such a visual hierarchy is crucial to recognize the complex relations of visual elements, leading to a comprehensive scene understanding. In this paper, we propose a Visual Hierarchy Mapper (Hi-Mapper), a novel approach for enhancing the structured understanding of the pre-trained Deep Neural Networks (DNNs). Hi-Mapper investigates the hierarchical organization of the visual scene by 1) pre-defining a hierarchy tree through the encapsulation of probability densities; and 2) learning the hierarchical relations in hyperbolic space with a novel hierarchical contrastive loss. The pre-defined hierarchy tree recursively interacts with the visual features of the pre-trained DNNs through hierarchy decomposition and encoding procedures, thereby effectively identifying the visual hierarchy and enhancing the recognition of an entire scene. Extensive experiments demonstrate that Hi-Mapper significantly enhances the representation capability of DNNs, leading to an improved performance on various tasks, including image classification and dense prediction tasks.

Eungbean Lee, Somi Jeong, Kwanghoon Sohn

Exemplar-guided image translation, synthesizing photo-realistic images that conform to both structural control and style exemplars, is attracting attention due to its ability to enhance user control over style manipulation. Previous methodologies have predominantly depended on establishing dense correspondences across cross-domain inputs. Despite these efforts, they incur quadratic memory and computational costs for establishing dense correspondence, resulting in limited versatility and performance degradation. In this paper, we propose a novel approach termed Exemplar-guided Image Translation with Brownian-Bridge Diffusion Models (EBDM). Our method formulates the task as a stochastic Brownian bridge process, a diffusion process with a fixed initial point as structure control and translates into the corresponding photo-realistic image while being conditioned solely on the given exemplar image. To efficiently guide the diffusion process toward the style of exemplar, we delineate three pivotal components: the Global Encoder, the Exemplar Network, and the Exemplar Attention Module to incorporate global and detailed texture information from exemplar images. Leveraging Bridge diffusion, the network can translate images from structure control while exclusively conditioned on the exemplar style, leading to more robust training and inference processes. We illustrate the superiority of our method over competing approaches through comprehensive benchmark evaluations and visual results.

Kwonyoung Kim, Jungin Park, Jin Kim et al.

Parameter-efficient tuning (PET) aims to transfer pre-trained foundation models to downstream tasks by learning a small number of parameters. Compared to traditional fine-tuning, which updates the entire model, PET significantly reduces storage and transfer costs for each task regardless of exponentially increasing pre-trained model capacity. However, most PET methods inherit the inference latency of their large backbone models and often introduce additional computational overhead due to additional modules (e.g. adapters), limiting their practicality for compute-intensive applications. In this paper, we propose Faster Parameter-Efficient Tuning (FPET), a novel approach that enhances inference speed and training efficiency while maintaining high storage efficiency. Specifically, we introduce a plug-and-play token redundancy reduction module delicately designed for PET. This module refines tokens from the self-attention layer using an adapter to learn the accurate similarity between tokens and cuts off the tokens through a fully-differentiable token merging strategy, which uses a straight-through estimator for optimal token reduction. Experimental results prove that our FPET achieves faster inference and higher memory efficiency than the pre-trained backbone while keeping competitive performance on par with state-of-the-art PET methods.

Jinbae Seo, Hyeongjun Kwon, Kwonyoung Kim et al.

Audiovisual instance segmentation (AVIS) requires accurately localizing and tracking sounding objects throughout video sequences. Existing methods suffer from visual bias stemming from two fundamental issues: uniform additive fusion prevents queries from specializing to different sound sources, while visual-only training objectives allow queries to converge to arbitrary salient objects. We propose Audio-Centric Query Generation using cross-attention, enabling each query to selectively attend to distinct sound sources and carry sound-specific priors into visual decoding. Additionally, we introduce Sound-Aware Ordinal Counting (SAOC) loss that explicitly supervises sounding object numbers through ordinal regression with monotonic consistency constraints, preventing visual-only convergence during training. Experiments on AVISeg benchmark demonstrate consistent improvements: +1.64 mAP, +0.6 HOTA, and +2.06 FSLA, validating that query specialization and explicit counting supervision are crucial for accurate audiovisual instance segmentation.

Jinhyun Jang, Jiyoung Lee, Kwanghoon Sohn

Image-text matching aims to build correspondences between visual and textual data by learning their pairwise similarities. Most existing approaches have adopted sparse binary supervision, indicating whether a pair of images and sentences matches or not. However, such sparse supervision covers a limited subset of image-text relationships, neglecting their inherent many-to-many correspondences; an image can be described in numerous texts at different descriptive levels. Moreover, existing approaches overlook the implicit connections from general to specific descriptions, which form the underlying rationale for the many-to-many relationships between vision and language. In this work, we propose descriptive image-text matching, called DITM, to learn the graded contextual similarity between image and text by exploring the descriptive flexibility of language. We formulate the descriptiveness score of each sentence with cumulative term frequency-inverse document frequency (TF-IDF) to balance the pairwise similarity according to the keywords in the sentence. Our method leverages sentence descriptiveness to learn robust image-text matching in two key ways: (1) to refine the false negative labeling, dynamically relaxing the connectivity between positive and negative pairs, and (2) to build more precise matching, aligning a set of relevant sentences in a generic-to-specific order. By moving beyond rigid binary supervision, DITM enhances the discovery of both optimal matches and potential positive pairs. Extensive experiments on MS-COCO, Flickr30K, and CxC datasets demonstrate the effectiveness of our method in representing complex image-text relationships compared to state-of-the-art approaches. In addition, DITM enhances the hierarchical reasoning ability of the model, supported by the extensive analysis on HierarCaps benchmark.

Taeyong Song, Sunok Kim, SungTai Kim et al.

Shape deformation of targets in SAR image due to random orientation and partial information loss caused by occlusion of the radar signal, is an essential challenge in SAR ship detection. In this paper, we propose a data augmentation method to train a deep network that is robust to partial information loss within the targets. Taking advantage of ground-truth annotations for bounding box and instance segmentation mask, we present a simple and effective pipeline to simulate information loss on targets in instance-level, while preserving contextual information. Furthermore, we adopt deformable convolutional network to adaptively extract shape-invariant deep features from geometrically translated targets. By learning sampling offset to the grid of standard convolution, the network can robustly extract the features from targets with shape variations for SAR ship detection. Experiments on the HRSID dataset including comparisons with other deep networks and augmentation methods, as well as ablation study, demonstrate the effectiveness of our proposed method.

Somi Jeong, Jiyoung Lee, Kwanghoon Sohn

Over the past few years, image-to-image (I2I) translation methods have been proposed to translate a given image into diverse outputs. Despite the impressive results, they mainly focus on the I2I translation between two domains, so the multi-domain I2I translation still remains a challenge. To address this problem, we propose a novel multi-domain unsupervised image-to-image translation (MDUIT) framework that leverages the decomposed content feature and appearance adaptive convolution to translate an image into a target appearance while preserving the given geometric content. We also exploit a contrast learning objective, which improves the disentanglement ability and effectively utilizes multi-domain image data in the training process by pairing the semantically similar images. This allows our method to learn the diverse mappings between multiple visual domains with only a single framework. We show that the proposed method produces visually diverse and plausible results in multiple domains compared to the state-of-the-art methods.

Jaehoon Cho, Seungryong Kim, Kwanghoon Sohn

This paper addresses the problem of single image de-raining, that is, the task of recovering clean and rain-free background scenes from a single image obscured by a rainy artifact. Although recent advances adopt real-world time-lapse data to overcome the need for paired rain-clean images, they are limited to fully exploit the time-lapse data. The main cause is that, in terms of network architectures, they could not capture long-term rain streak information in the time-lapse data during training owing to the lack of memory components. To address this problem, we propose a novel network architecture based on a memory network that explicitly helps to capture long-term rain streak information in the time-lapse data. Our network comprises the encoder-decoder networks and a memory network. The features extracted from the encoder are read and updated in the memory network that contains several memory items to store rain streak-aware feature representations. With the read/update operation, the memory network retrieves relevant memory items in terms of the queries, enabling the memory items to represent the various rain streaks included in the time-lapse data. To boost the discriminative power of memory features, we also present a novel background selective whitening (BSW) loss for capturing only rain streak information in the memory network by erasing the background information. Experimental results on standard benchmarks demonstrate the effectiveness and superiority of our approach.

Jaehoon Cho, Dongbo Min, Youngjung Kim et al.

This manual is intended to provide a detailed description of the DIML/CVL RGB-D dataset. This dataset is comprised of 2M color images and their corresponding depth maps from a great variety of natural indoor and outdoor scenes. The indoor dataset was constructed using the Microsoft Kinect v2, while the outdoor dataset was built using the stereo cameras (ZED stereo camera and built-in stereo camera). Table I summarizes the details of our dataset, including acquisition, processing, format, and toolbox. Refer to Section II and III for more details.

Jaehoon Cho, Jiyoung Lee, Changjae Oh et al.

Video prediction, forecasting the future frames from a sequence of input frames, is a challenging task since the view changes are influenced by various factors, such as the global context surrounding the scene and local motion dynamics. In this paper, we propose a new framework to integrate these complementary attributes to predict complex pixel dynamics through deep networks. We present global context propagation networks that iteratively aggregate the non-local neighboring representations to preserve the contextual information over the past frames. To capture the local motion pattern of objects, we also devise local filter memory networks that generate adaptive filter kernels by storing the prototypical motion of moving objects in the memory. The proposed framework, utilizing the outputs from both networks, can address blurry predictions and color distortion. We conduct experiments on Caltech pedestrian and UCF101 datasets, and demonstrate state-of-the-art results. Especially for multi-step prediction, we obtain an outstanding performance in quantitative and qualitative evaluation.

Jin Kim, Jiyoung Lee, Jungin Park et al.

Domain generalization aims to learn a prediction model on multi-domain source data such that the model can generalize to a target domain with unknown statistics. Most existing approaches have been developed under the assumption that the source data is well-balanced in terms of both domain and class. However, real-world training data collected with different composition biases often exhibits severe distribution gaps for domain and class, leading to substantial performance degradation. In this paper, we propose a self-balanced domain generalization framework that adaptively learns the weights of losses to alleviate the bias caused by different distributions of the multi-domain source data. The self-balanced scheme is based on an auxiliary reweighting network that iteratively updates the weight of loss conditioned on the domain and class information by leveraging balanced meta data. Experimental results demonstrate the effectiveness of our method overwhelming state-of-the-art works for domain generalization.

Sunghun Joung, Seungryong Kim, Minsu Kim et al.

We propose a novel framework for fine-grained object recognition that learns to recover object variation in 3D space from a single image, trained on an image collection without using any ground-truth 3D annotation. We accomplish this by representing an object as a composition of 3D shape and its appearance, while eliminating the effect of camera viewpoint, in a canonical configuration. Unlike conventional methods modeling spatial variation in 2D images only, our method is capable of reconfiguring the appearance feature in a canonical 3D space, thus enabling the subsequent object classifier to be invariant under 3D geometric variation. Our representation also allows us to go beyond existing methods, by incorporating 3D shape variation as an additional cue for object recognition. To learn the model without ground-truth 3D annotation, we deploy a differentiable renderer in an analysis-by-synthesis framework. By incorporating 3D shape and appearance jointly in a deep representation, our method learns the discriminative representation of the object and achieves competitive performance on fine-grained image recognition and vehicle re-identification. We also demonstrate that the performance of 3D shape reconstruction is improved by learning fine-grained shape deformation in a boosting manner.

Daniel McDuff, Yale Song, Jiyoung Lee et al.

The ability to perform causal and counterfactual reasoning are central properties of human intelligence. Decision-making systems that can perform these types of reasoning have the potential to be more generalizable and interpretable. Simulations have helped advance the state-of-the-art in this domain, by providing the ability to systematically vary parameters (e.g., confounders) and generate examples of the outcomes in the case of counterfactual scenarios. However, simulating complex temporal causal events in multi-agent scenarios, such as those that exist in driving and vehicle navigation, is challenging. To help address this, we present a high-fidelity simulation environment that is designed for developing algorithms for causal discovery and counterfactual reasoning in the safety-critical context. A core component of our work is to introduce \textit{agency}, such that it is simple to define and create complex scenarios using high-level definitions. The vehicles then operate with agency to complete these objectives, meaning low-level behaviors need only be controlled if necessary. We perform experiments with three state-of-the-art methods to create baselines and highlight the affordances of this environment. Finally, we highlight challenges and opportunities for future work.

Seokju Cho, Sunghwan Hong, Sangryul Jeon et al.

We propose a novel cost aggregation network, called Cost Aggregation Transformers (CATs), to find dense correspondences between semantically similar images with additional challenges posed by large intra-class appearance and geometric variations. Cost aggregation is a highly important process in matching tasks, which the matching accuracy depends on the quality of its output. Compared to hand-crafted or CNN-based methods addressing the cost aggregation, in that either lacks robustness to severe deformations or inherit the limitation of CNNs that fail to discriminate incorrect matches due to limited receptive fields, CATs explore global consensus among initial correlation map with the help of some architectural designs that allow us to fully leverage self-attention mechanism. Specifically, we include appearance affinity modeling to aid the cost aggregation process in order to disambiguate the noisy initial correlation maps and propose multi-level aggregation to efficiently capture different semantics from hierarchical feature representations. We then combine with swapping self-attention technique and residual connections not only to enforce consistent matching but also to ease the learning process, which we find that these result in an apparent performance boost. We conduct experiments to demonstrate the effectiveness of the proposed model over the latest methods and provide extensive ablation studies. Project page is available at : https://sunghwanhong.github.io/CATs/.

Jungin Park, Jiyoung Lee, Kwanghoon Sohn

This paper presents a novel method, termed Bridge to Answer, to infer correct answers for questions about a given video by leveraging adequate graph interactions of heterogeneous crossmodal graphs. To realize this, we learn question conditioned visual graphs by exploiting the relation between video and question to enable each visual node using question-to-visual interactions to encompass both visual and linguistic cues. In addition, we propose bridged visual-to-visual interactions to incorporate two complementary visual information on appearance and motion by placing the question graph as an intermediate bridge. This bridged architecture allows reliable message passing through compositional semantics of the question to generate an appropriate answer. As a result, our method can learn the question conditioned visual representations attributed to appearance and motion that show powerful capability for video question answering. Extensive experiments prove that the proposed method provides effective and superior performance than state-of-the-art methods on several benchmarks.

Somi Jeong, Youngjung Kim, Eungbean Lee et al.

We present a novel unsupervised framework for instance-level image-to-image translation. Although recent advances have been made by incorporating additional object annotations, existing methods often fail to handle images with multiple disparate objects. The main cause is that, during inference, they apply a global style to the whole image and do not consider the large style discrepancy between instance and background, or within instances. To address this problem, we propose a class-aware memory network that explicitly reasons about local style variations. A key-values memory structure, with a set of read/update operations, is introduced to record class-wise style variations and access them without requiring an object detector at the test time. The key stores a domain-agnostic content representation for allocating memory items, while the values encode domain-specific style representations. We also present a feature contrastive loss to boost the discriminative power of memory items. We show that by incorporating our memory, we can transfer class-aware and accurate style representations across domains. Experimental results demonstrate that our model outperforms recent instance-level methods and achieves state-of-the-art performance.

Jiyoung Lee, Soo-Whan Chung, Sunok Kim et al.

In this paper, we address the problem of separating individual speech signals from videos using audio-visual neural processing. Most conventional approaches utilize frame-wise matching criteria to extract shared information between co-occurring audio and video. Thus, their performance heavily depends on the accuracy of audio-visual synchronization and the effectiveness of their representations. To overcome the frame discontinuity problem between two modalities due to transmission delay mismatch or jitter, we propose a cross-modal affinity network (CaffNet) that learns global correspondence as well as locally-varying affinities between audio and visual streams. Given that the global term provides stability over a temporal sequence at the utterance-level, this resolves the label permutation problem characterized by inconsistent assignments. By extending the proposed cross-modal affinity on the complex network, we further improve the separation performance in the complex spectral domain. Experimental results verify that the proposed methods outperform conventional ones on various datasets, demonstrating their advantages in real-world scenarios.

Matteo Poggi, Seungryong Kim, Fabio Tosi et al.

Stereo matching is one of the most popular techniques to estimate dense depth maps by finding the disparity between matching pixels on two, synchronized and rectified images. Alongside with the development of more accurate algorithms, the research community focused on finding good strategies to estimate the reliability, i.e. the confidence, of estimated disparity maps. This information proves to be a powerful cue to naively find wrong matches as well as to improve the overall effectiveness of a variety of stereo algorithms according to different strategies. In this paper, we review more than ten years of developments in the field of confidence estimation for stereo matching. We extensively discuss and evaluate existing confidence measures and their variants, from hand-crafted ones to the most recent, state-of-the-art learning based methods. We study the different behaviors of each measure when applied to a pool of different stereo algorithms and, for the first time in literature, when paired with a state-of-the-art deep stereo network. Our experiments, carried out on five different standard datasets, provide a comprehensive overview of the field, highlighting in particular both strengths and limitations of learning-based strategies.

Minsu Kim, Sunghun Joung, Seungryong Kim et al.

Existing techniques to adapt semantic segmentation networks across the source and target domains within deep convolutional neural networks (CNNs) deal with all the samples from the two domains in a global or category-aware manner. They do not consider an inter-class variation within the target domain itself or estimated category, providing the limitation to encode the domains having a multi-modal data distribution. To overcome this limitation, we introduce a learnable clustering module, and a novel domain adaptation framework called cross-domain grouping and alignment. To cluster the samples across domains with an aim to maximize the domain alignment without forgetting precise segmentation ability on the source domain, we present two loss functions, in particular, for encouraging semantic consistency and orthogonality among the clusters. We also present a loss so as to solve a class imbalance problem, which is the other limitation of the previous methods. Our experiments show that our method consistently boosts the adaptation performance in semantic segmentation, outperforming the state-of-the-arts on various domain adaptation settings.

Hyesong Choi, Hunsang Lee, Sunkyung Kim et al.

Self-supervised monocular depth estimation has become an appealing solution to the lack of ground truth labels, but its reconstruction loss often produces over-smoothed results across object boundaries and is incapable of handling occlusion explicitly. In this paper, we propose a new approach to leverage pseudo ground truth depth maps of stereo images generated from self-supervised stereo matching methods. The confidence map of the pseudo ground truth depth map is estimated to mitigate performance degeneration by inaccurate pseudo depth maps. To cope with the prediction error of the confidence map itself, we also leverage the threshold network that learns the threshold dynamically conditioned on the pseudo depth maps. The pseudo depth labels filtered out by the thresholded confidence map are used to supervise the monocular depth network. Furthermore, we propose the probabilistic framework that refines the monocular depth map with the help of its uncertainty map through the pixel-adaptive convolution (PAC) layer. Experimental results demonstrate superior performance to state-of-the-art monocular depth estimation methods. Lastly, we exhibit that the proposed threshold learning can also be used to improve the performance of existing confidence estimation approaches.

Jungin Park, Jiyoung Lee, Ig-Jae Kim et al.

The goal of video summarization is to select keyframes that are visually diverse and can represent a whole story of an input video. State-of-the-art approaches for video summarization have mostly regarded the task as a frame-wise keyframe selection problem by aggregating all frames with equal weight. However, to find informative parts of the video, it is necessary to consider how all the frames of the video are related to each other. To this end, we cast video summarization as a graph modeling problem. We propose recursive graph modeling networks for video summarization, termed SumGraph, to represent a relation graph, where frames are regarded as nodes and nodes are connected by semantic relationships among frames. Our networks accomplish this through a recursive approach to refine an initially estimated graph to correctly classify each node as a keyframe by reasoning the graph representation via graph convolutional networks. To leverage SumGraph in a more practical environment, we also present a way to adapt our graph modeling in an unsupervised fashion. With SumGraph, we achieved state-of-the-art performance on several benchmarks for video summarization in both supervised and unsupervised manners.

Sunghun Joung, Seungryong Kim, Hanjae Kim et al.

Existing techniques to encode spatial invariance within deep convolutional neural networks only model 2D transformation fields. This does not account for the fact that objects in a 2D space are a projection of 3D ones, and thus they have limited ability to severe object viewpoint changes. To overcome this limitation, we introduce a learnable module, cylindrical convolutional networks (CCNs), that exploit cylindrical representation of a convolutional kernel defined in the 3D space. CCNs extract a view-specific feature through a view-specific convolutional kernel to predict object category scores at each viewpoint. With the view-specific feature, we simultaneously determine objective category and viewpoints using the proposed sinusoidal soft-argmax module. Our experiments demonstrate the effectiveness of the cylindrical convolutional networks on joint object detection and viewpoint estimation.

Sangryul Jeon, Dongbo Min, Seungryong Kim et al.

Convolutional neural networks (CNNs) based approaches for semantic alignment and object landmark detection have improved their performance significantly. Current efforts for the two tasks focus on addressing the lack of massive training data through weakly- or unsupervised learning frameworks. In this paper, we present a joint learning approach for obtaining dense correspondences and discovering object landmarks from semantically similar images. Based on the key insight that the two tasks can mutually provide supervisions to each other, our networks accomplish this through a joint loss function that alternatively imposes a consistency constraint between the two tasks, thereby boosting the performance and addressing the lack of training data in a principled manner. To the best of our knowledge, this is the first attempt to address the lack of training data for the two tasks through the joint learning. To further improve the robustness of our framework, we introduce a probabilistic learning formulation that allows only reliable matches to be used in the joint learning process. With the proposed method, state-of-the-art performance is attained on several standard benchmarks for semantic matching and landmark detection, including a newly introduced dataset, JLAD, which contains larger number of challenging image pairs than existing datasets.

Jiyoung Lee, Seungryong Kim, Sunok Kim et al.

Traditional techniques for emotion recognition have focused on the facial expression analysis only, thus providing limited ability to encode context that comprehensively represents the emotional responses. We present deep networks for context-aware emotion recognition, called CAER-Net, that exploit not only human facial expression but also context information in a joint and boosting manner. The key idea is to hide human faces in a visual scene and seek other contexts based on an attention mechanism. Our networks consist of two sub-networks, including two-stream encoding networks to seperately extract the features of face and context regions, and adaptive fusion networks to fuse such features in an adaptive fashion. We also introduce a novel benchmark for context-aware emotion recognition, called CAER, that is more appropriate than existing benchmarks both qualitatively and quantitatively. On several benchmarks, CAER-Net proves the effect of context for emotion recognition. Our dataset is available at http://caer-dataset.github.io.

Jaehoon Cho, Dongbo Min, Youngjung Kim et al.

Current self-supervised methods for monocular depth estimation are largely based on deeply nested convolutional networks that leverage stereo image pairs or monocular sequences during a training phase. However, they often exhibit inaccurate results around occluded regions and depth boundaries. In this paper, we present a simple yet effective approach for monocular depth estimation using stereo image pairs. The study aims to propose a student-teacher strategy in which a shallow student network is trained with the auxiliary information obtained from a deeper and more accurate teacher network. Specifically, we first train the stereo teacher network by fully utilizing the binocular perception of 3-D geometry and then use the depth predictions of the teacher network to train the student network for monocular depth inference. This enables us to exploit all available depth data from massive unlabeled stereo pairs. We propose a strategy that involves the use of a data ensemble to merge the multiple depth predictions of the teacher network to improve the training samples by collecting non-trivial knowledge beyond a single prediction. To refine the inaccurate depth estimation that is used when training the student network, we further propose stereo confidence-guided regression loss that handles the unreliable pseudo depth values in occlusion, texture-less region, and repetitive pattern. To complement the existing dataset comprising outdoor driving scenes, we built a novel large-scale dataset consisting of one million outdoor stereo images taken using hand-held stereo cameras. Finally, we demonstrate that the monocular depth estimation network provides feature representations that are suitable for high-level vision tasks. The experimental results for various outdoor scenarios demonstrate the effectiveness and flexibility of our approach, which outperforms state-of-the-art approaches.

Seungryong Kim, Dongbo Min, Somi Jeong et al.

We present semantic attribute matching networks (SAM-Net) for jointly establishing correspondences and transferring attributes across semantically similar images, which intelligently weaves the advantages of the two tasks while overcoming their limitations. SAM-Net accomplishes this through an iterative process of establishing reliable correspondences by reducing the attribute discrepancy between the images and synthesizing attribute transferred images using the learned correspondences. To learn the networks using weak supervisions in the form of image pairs, we present a semantic attribute matching loss based on the matching similarity between an attribute transferred source feature and a warped target feature. With SAM-Net, the state-of-the-art performance is attained on several benchmarks for semantic matching and attribute transfer.

Seungryong Kim, Stephen Lin, Sangryul Jeon et al.

We present recurrent transformer networks (RTNs) for obtaining dense correspondences between semantically similar images. Our networks accomplish this through an iterative process of estimating spatial transformations between the input images and using these transformations to generate aligned convolutional activations. By directly estimating the transformations between an image pair, rather than employing spatial transformer networks to independently normalize each individual image, we show that greater accuracy can be achieved. This process is conducted in a recursive manner to refine both the transformation estimates and the feature representations. In addition, a technique is presented for weakly-supervised training of RTNs that is based on a proposed classification loss. With RTNs, state-of-the-art performance is attained on several benchmarks for semantic correspondence.

Sangryul Jeon, Seungryong Kim, Dongbo Min et al.

This paper presents a deep architecture for dense semantic correspondence, called pyramidal affine regression networks (PARN), that estimates locally-varying affine transformation fields across images. To deal with intra-class appearance and shape variations that commonly exist among different instances within the same object category, we leverage a pyramidal model where affine transformation fields are progressively estimated in a coarse-to-fine manner so that the smoothness constraint is naturally imposed within deep networks. PARN estimates residual affine transformations at each level and composes them to estimate final affine transformations. Furthermore, to overcome the limitations of insufficient training data for semantic correspondence, we propose a novel weakly-supervised training scheme that generates progressive supervisions by leveraging a correspondence consistency across image pairs. Our method is fully learnable in an end-to-end manner and does not require quantizing infinite continuous affine transformation fields. To the best of our knowledge, it is the first work that attempts to estimate dense affine transformation fields in a coarse-to-fine manner within deep networks. Experimental results demonstrate that PARN outperforms the state-of-the-art methods for dense semantic correspondence on various benchmarks.

Seungryong Kim, Dongbo Min, Stephen Lin et al.

Techniques for dense semantic correspondence have provided limited ability to deal with the geometric variations that commonly exist between semantically similar images. While variations due to scale and rotation have been examined, there lack practical solutions for more complex deformations such as affine transformations because of the tremendous size of the associated solution space. To address this problem, we present a discrete-continuous transformation matching (DCTM) framework where dense affine transformation fields are inferred through a discrete label optimization in which the labels are iteratively updated via continuous regularization. In this way, our approach draws solutions from the continuous space of affine transformations in a manner that can be computed efficiently through constant-time edge-aware filtering and a proposed affine-varying CNN-based descriptor. Experimental results show that this model outperforms the state-of-the-art methods for dense semantic correspondence on various benchmarks.