Kyoobin Lee

Sungho Shin, Joosoon Lee, Junseok Lee et al.

Deep learning has achieved outstanding performance for face recognition benchmarks, but performance reduces significantly for low resolution (LR) images. We propose an attention similarity knowledge distillation approach, which transfers attention maps obtained from a high resolution (HR) network as a teacher into an LR network as a student to boost LR recognition performance. Inspired by humans being able to approximate an object's region from an LR image based on prior knowledge obtained from HR images, we designed the knowledge distillation loss using the cosine similarity to make the student network's attention resemble the teacher network's attention. Experiments on various LR face related benchmarks confirmed the proposed method generally improved recognition performances on LR settings, outperforming state-of-the-art results by simply transferring well-constructed attention maps. The code and pretrained models are publicly available in the https://github.com/gist-ailab/teaching-where-to-look.

Seongju Lee, Junseok Lee, Yeonguk Yu et al.

Multi-agent trajectory prediction is crucial to autonomous driving and understanding the surrounding environment. Learning-based approaches for multi-agent trajectory prediction, such as primarily relying on graph neural networks, graph transformers, and hypergraph neural networks, have demonstrated outstanding performance on real-world datasets in recent years. However, the hypergraph transformer-based method for trajectory prediction is yet to be explored. Therefore, we present a MultiscAle Relational Transformer (MART) network for multi-agent trajectory prediction. MART is a hypergraph transformer architecture to consider individual and group behaviors in transformer machinery. The core module of MART is the encoder, which comprises a Pair-wise Relational Transformer (PRT) and a Hyper Relational Transformer (HRT). The encoder extends the capabilities of a relational transformer by introducing HRT, which integrates hyperedge features into the transformer mechanism, promoting attention weights to focus on group-wise relations. In addition, we propose an Adaptive Group Estimator (AGE) designed to infer complex group relations in real-world environments. Extensive experiments on three real-world datasets (NBA, SDD, and ETH-UCY) demonstrate that our method achieves state-of-the-art performance, enhancing ADE/FDE by 3.9%/11.8% on the NBA dataset. Code is available at https://github.com/gist-ailab/MART.

Sungho Shin, Yeonguk Yu, Kyoobin Lee

In this study, we introduce a feature knowledge distillation framework to improve low-resolution (LR) face recognition performance using knowledge obtained from high-resolution (HR) images. The proposed framework transfers informative features from an HR-trained network to an LR-trained network by reducing the distance between them. A cosine similarity measure was employed as a distance metric to effectively align the HR and LR features. This approach differs from conventional knowledge distillation frameworks, which use the L_p distance metrics and offer the advantage of converging well when reducing the distance between features of different resolutions. Our framework achieved a 3% improvement over the previous state-of-the-art method on the AgeDB-30 benchmark without bells and whistles, while maintaining a strong performance on HR images. The effectiveness of cosine similarity as a distance metric was validated through statistical analysis, making our approach a promising solution for real-world applications in which LR images are frequently encountered. The code and pretrained models are publicly available on https://github.com/gist-ailab/feature-similarity-KD.

Seongju Lee, Yeonguk Yu, Seunghyeok Back et al.

Automatic sleep scoring is essential for the diagnosis and treatment of sleep disorders and enables longitudinal sleep tracking in home environments. Conventionally, learning-based automatic sleep scoring on single-channel electroencephalogram (EEG) is actively studied because obtaining multi-channel signals during sleep is difficult. However, learning representation from raw EEG signals is challenging owing to the following issues: 1) sleep-related EEG patterns occur on different temporal and frequency scales and 2) sleep stages share similar EEG patterns. To address these issues, we propose a deep learning framework named SleePyCo that incorporates 1) a feature pyramid and 2) supervised contrastive learning for automatic sleep scoring. For the feature pyramid, we propose a backbone network named SleePyCo-backbone to consider multiple feature sequences on different temporal and frequency scales. Supervised contrastive learning allows the network to extract class discriminative features by minimizing the distance between intra-class features and simultaneously maximizing that between inter-class features. Comparative analyses on four public datasets demonstrate that SleePyCo consistently outperforms existing frameworks based on single-channel EEG. Extensive ablation experiments show that SleePyCo exhibits enhanced overall performance, with significant improvements in discrimination between the N1 and rapid eye movement (REM) stages.

Yeonguk Yu, Sungho Shin, Seongju Lee et al.

Detecting out-of-distribution (OOD) inputs during the inference stage is crucial for deploying neural networks in the real world. Previous methods commonly relied on the output of a network derived from the highly activated feature map. In this study, we first revealed that a norm of the feature map obtained from the other block than the last block can be a better indicator of OOD detection. Motivated by this, we propose a simple framework consisting of FeatureNorm: a norm of the feature map and NormRatio: a ratio of FeatureNorm for ID and OOD to measure the OOD detection performance of each block. In particular, to select the block that provides the largest difference between FeatureNorm of ID and FeatureNorm of OOD, we create Jigsaw puzzle images as pseudo OOD from ID training samples and calculate NormRatio, and the block with the largest value is selected. After the suitable block is selected, OOD detection with the FeatureNorm outperforms other OOD detection methods by reducing FPR95 by up to 52.77% on CIFAR10 benchmark and by up to 48.53% on ImageNet benchmark. We demonstrate that our framework can generalize to various architectures and the importance of block selection, which can improve previous OOD detection methods as well.

Benjamin Kiefer, Jan Lukas Augustin, Jon Muhovič et al.

The 4th Workshop on Maritime Computer Vision (MaCVi) is organized as part of CVPR 2026. This edition features five benchmark challenges with emphasis on both predictive accuracy and embedded real-time feasibility. This report summarizes the MaCVi 2026 challenge setup, evaluation protocols, datasets, and benchmark tracks, and presents quantitative results, qualitative comparisons, and cross-challenge analyses of emerging method trends. We also include technical reports from top-performing teams to highlight practical design choices and lessons learned across the benchmark suite. Datasets, leaderboards, and challenge resources are available at https://macvi.org/workshop/cvpr26.

Seunghyeok Back, Sangbeom Lee, Kangmin Kim et al.

Accurate and efficient segmentation of unknown objects in unstructured environments is essential for robotic manipulation. Unknown Object Instance Segmentation (UOIS), which aims to identify all objects in unknown categories and backgrounds, has become a key capability for various robotic tasks. However, existing methods struggle with over-segmentation and under-segmentation, leading to failures in manipulation tasks such as grasping. To address these challenges, we propose QuBER (Quadruple Boundary Error Refinement), a novel error-informed refinement approach for high-quality UOIS. QuBER first estimates quadruple boundary errors-true positive, true negative, false positive, and false negative pixels-at the instance boundaries of the initial segmentation. It then refines the segmentation using an error-guided fusion mechanism, effectively correcting both fine-grained and instance-level segmentation errors. Extensive evaluations on three public benchmarks demonstrate that QuBER outperforms state-of-the-art methods and consistently improves various UOIS methods while maintaining a fast inference time of less than 0.1 seconds. Furthermore, we show that QuBER improves the success rate of grasping target objects in cluttered environments. Code and supplementary materials are available at https://sites.google.com/view/uois-quber.

Kangmin Kim, Seunghyeok Back, Geonhyup Lee et al.

Bimanual grasping is essential for robots to handle large and complex objects. However, existing methods either focus solely on single-arm grasping or employ separate grasp generation and bimanual evaluation stages, leading to coordination problems including collision risks and unbalanced force distribution. To address these limitations, we propose BiGraspFormer, a unified end-to-end transformer framework that directly generates coordinated bimanual grasps from object point clouds. Our key idea is the Single-Guided Bimanual (SGB) strategy, which first generates diverse single grasp candidates using a transformer decoder, then leverages their learned features through specialized attention mechanisms to jointly predict bimanual poses and quality scores. This conditioning strategy reduces the complexity of the 12-DoF search space while ensuring coordinated bimanual manipulation. Comprehensive simulation experiments and real-world validation demonstrate that BiGraspFormer consistently outperforms existing methods while maintaining efficient inference speed (<0.05s), confirming the effectiveness of our framework. Code and supplementary materials are available at https://sites.google.com/view/bigraspformer

Yeonguk Yu, Sungho Shin, Seunghyeok Back et al.

Test-time adaptation (TTA) aims to adapt a pre-trained model to a new test domain without access to source data after deployment. Existing approaches typically rely on self-training with pseudo-labels since ground-truth cannot be obtained from test data. Although the quality of pseudo labels is important for stable and accurate long-term adaptation, it has not been previously addressed. In this work, we propose DPLOT, a simple yet effective TTA framework that consists of two components: (1) domain-specific block selection and (2) pseudo-label generation using paired-view images. Specifically, we select blocks that involve domain-specific feature extraction and train these blocks by entropy minimization. After blocks are adjusted for current test domain, we generate pseudo-labels by averaging given test images and corresponding flipped counterparts. By simply using flip augmentation, we prevent a decrease in the quality of the pseudo-labels, which can be caused by the domain gap resulting from strong augmentation. Our experimental results demonstrate that DPLOT outperforms previous TTA methods in CIFAR10-C, CIFAR100-C, and ImageNet-C benchmarks, reducing error by up to 5.4%, 9.1%, and 2.9%, respectively. Also, we provide an extensive analysis to demonstrate effectiveness of our framework. Code is available at https://github.com/gist-ailab/domain-specific-block-selection-and-paired-view-pseudo-labeling-for-online-TTA.

Junseok Lee, Sungho Shin, Seongju Lee et al.

Single-domain generalization is essential for object detection, particularly when training models on a single source domain and evaluating them on unseen target domains. Domain shifts, such as changes in weather, lighting, or scene conditions, pose significant challenges to the generalization ability of existing models. To address this, we propose Cross-Domain Feature Knowledge Distillation (CD-FKD), which enhances the generalization capability of the student network by leveraging both global and instance-wise feature distillation. The proposed method uses diversified data through downscaling and corruption to train the student network, whereas the teacher network receives the original source domain data. The student network mimics the features of the teacher through both global and instance-wise distillation, enabling it to extract object-centric features effectively, even for objects that are difficult to detect owing to corruption. Extensive experiments on challenging scenes demonstrate that CD-FKD outperforms state-of-the-art methods in both target domain generalization and source domain performance, validating its effectiveness in improving object detection robustness to domain shifts. This approach is valuable in real-world applications, like autonomous driving and surveillance, where robust object detection in diverse environments is crucial.

Geonhyup Lee, Joosoon Lee, Sangjun Noh et al.

The study addresses the foundational and challenging task of peg-in-hole assembly in robotics, where misalignments caused by sensor inaccuracies and mechanical errors often result in insertion failures or jamming. This research introduces PolyFit, representing a paradigm shift by transitioning from a reinforcement learning approach to a supervised learning methodology. PolyFit is a Force/Torque (F/T)-based supervised learning framework designed for 5-DoF peg-in-hole assembly. It utilizes F/T data for accurate extrinsic pose estimation and adjusts the peg pose to rectify misalignments. Extensive training in a simulated environment involves a dataset encompassing a diverse range of peg-hole shapes, extrinsic poses, and their corresponding contact F/T readings. To enhance extrinsic pose estimation, a multi-point contact strategy is integrated into the model input, recognizing that identical F/T readings can indicate different poses. The study proposes a sim-to-real adaptation method for real-world application, using a sim-real paired dataset to enable effective generalization to complex and unseen polygon shapes. PolyFit achieves impressive peg-in-hole success rates of 97.3% and 96.3% for seen and unseen shapes in simulations, respectively. Real-world evaluations further demonstrate substantial success rates of 86.7% and 85.0%, highlighting the robustness and adaptability of the proposed method.

Yeonguk Yu, Minhwan Ko, Sungho Shin et al.

Deep neural networks have demonstrated remarkable performance in various vision tasks, but their success heavily depends on the quality of the training data. Noisy labels are a critical issue in medical datasets and can significantly degrade model performance. Previous clean sample selection methods have not utilized the well pre-trained features of vision foundation models (VFMs) and assumed that training begins from scratch. In this paper, we propose CUFIT, a curriculum fine-tuning paradigm of VFMs for medical image classification under label noise. Our method is motivated by the fact that linear probing of VFMs is relatively unaffected by noisy samples, as it does not update the feature extractor of the VFM, thus robustly classifying the training samples. Subsequently, curriculum fine-tuning of two adapters is conducted, starting with clean sample selection from the linear probing phase. Our experimental results demonstrate that CUFIT outperforms previous methods across various medical image benchmarks. Specifically, our method surpasses previous baselines by 5.0%, 2.1%, 4.6%, and 5.8% at a 40% noise rate on the HAM10000, APTOS-2019, BloodMnist, and OrgancMnist datasets, respectively. Furthermore, we provide extensive analyses to demonstrate the impact of our method on noisy label detection. For instance, our method shows higher label precision and recall compared to previous approaches. Our work highlights the potential of leveraging VFMs in medical image classification under challenging conditions of noisy labels.

Benjamin Kiefer, Lojze Žust, Jon Muhovič et al.

The 3rd Workshop on Maritime Computer Vision (MaCVi) 2025 addresses maritime computer vision for Unmanned Surface Vehicles (USV) and underwater. This report offers a comprehensive overview of the findings from the challenges. We provide both statistical and qualitative analyses, evaluating trends from over 700 submissions. All datasets, evaluation code, and the leaderboard are available to the public at https://macvi.org/workshop/macvi25.

Seunghyeok Back, Joosoon Lee, Kangmin Kim et al.

Robust grasping in cluttered environments remains an open challenge in robotics. While benchmark datasets have significantly advanced deep learning methods, they mainly focus on simplistic scenes with light occlusion and insufficient diversity, limiting their applicability to practical scenarios. We present GraspClutter6D, a large-scale real-world grasping dataset featuring: (1) 1,000 highly cluttered scenes with dense arrangements (14.1 objects/scene, 62.6\% occlusion), (2) comprehensive coverage across 200 objects in 75 environment configurations (bins, shelves, and tables) captured using four RGB-D cameras from multiple viewpoints, and (3) rich annotations including 736K 6D object poses and 9.3B feasible robotic grasps for 52K RGB-D images. We benchmark state-of-the-art segmentation, object pose estimation, and grasp detection methods to provide key insights into challenges in cluttered environments. Additionally, we validate the dataset's effectiveness as a training resource, demonstrating that grasping networks trained on GraspClutter6D significantly outperform those trained on existing datasets in both simulation and real-world experiments. The dataset, toolkit, and annotation tools are publicly available on our project website: https://sites.google.com/view/graspclutter6d.

Junseok Lee, Jongwon Kim, Jumi Park et al.

This paper proposes a method to automatically detect the key feature parts in a CAD of commercial TV and monitor using a deep neural network. We developed a deep learning pipeline that can detect the injection parts such as hook, boss, undercut and press parts such as DPS, Embo-Screwless, Embo-Burring, and EMBO in the 2D CAD drawing images. We first cropped the drawing to a specific size for the training efficiency of a deep neural network. Then, we use Cascade R-CNN to find the position of injection and press parts and use Resnet-50 to predict the orientation of the parts. Finally, we convert the position of the parts found through the cropped image to the position of the original image. As a result, we obtained detection accuracy of injection and press parts with 84.1% in AP (Average Precision), 91.2% in AR(Average Recall), 72.0% in AP, 87.0% in AR, and orientation accuracy of injection and press parts with 94.4% and 92.0%, which can facilitate the faster design in industrial product design.

Seunghyeok Back, Joosoon Lee, Taewon Kim et al.

Instance-aware segmentation of unseen objects is essential for a robotic system in an unstructured environment. Although previous works achieved encouraging results, they were limited to segmenting the only visible regions of unseen objects. For robotic manipulation in a cluttered scene, amodal perception is required to handle the occluded objects behind others. This paper addresses Unseen Object Amodal Instance Segmentation (UOAIS) to detect 1) visible masks, 2) amodal masks, and 3) occlusions on unseen object instances. For this, we propose a Hierarchical Occlusion Modeling (HOM) scheme designed to reason about the occlusion by assigning a hierarchy to a feature fusion and prediction order. We evaluated our method on three benchmarks (tabletop, indoors, and bin environments) and achieved state-of-the-art (SOTA) performance. Robot demos for picking up occluded objects, codes, and datasets are available at https://sites.google.com/view/uoais

Joosoon Lee, Seongju Lee, Seunghyeok Back et al.

Understanding assembly instruction has the potential to enhance the robot s task planning ability and enables advanced robotic applications. To recognize the key components from the 2D assembly instruction image, We mainly focus on segmenting the speech bubble area, which contains lots of information about instructions. For this, We applied Cascade Mask R-CNN and developed a context-aware data augmentation scheme for speech bubble segmentation, which randomly combines images cuts by considering the context of assembly instructions. We showed that the proposed augmentation scheme achieves a better segmentation performance compared to the existing augmentation algorithm by increasing the diversity of trainable data while considering the distribution of components locations. Also, we showed that deep learning can be useful to understand assembly instruction by detecting the essential objects in the assembly instruction, such as tools and parts.

Jongwon Kim, Sungho Shin, Yeonguk Yu et al.

Privacy issues were raised in the process of training deep learning in medical, mobility, and other fields. To solve this problem, we present privacy-preserving distributed deep learning method that allow clients to learn a variety of data without direct exposure. We divided a single deep learning architecture into a common extractor, a cloud model and a local classifier for the distributed learning. First, the common extractor, which is used by local clients, extracts secure features from the input data. The secure features also take the role that the cloud model can employ various task and diverse types of data. The feature contain the most important information that helps to proceed various task. Second, the cloud model including most parts of the whole training model gets the embedded features from the massive local clients, and performs most of deep learning operations which takes severe computing cost. After the operations in cloud model finished, outputs of the cloud model send back to local clients. Finally, the local classifier determined classification results and delivers the results to local clients. When clients train models, our model does not directly expose sensitive information to exterior network. During the test, the average performance improvement was 2.63% over the existing local training model. However, in a distributed environment, there is a possibility of inversion attack due to exposed features. For this reason, we experimented with the common extractor to prevent data restoration. The quality of restoration of the original image was tested by adjusting the depth of the common extractor. As a result, we found that the deeper the common extractor, the restoration score decreased to 89.74.

Seunghyeok Back, Jongwon Kim, Raeyoung Kang et al.

Segmentation of unseen industrial parts is essential for autonomous industrial systems. However, industrial components are texture-less, reflective, and often found in cluttered and unstructured environments with heavy occlusion, which makes it more challenging to deal with unseen objects. To tackle this problem, we present a synthetic data generation pipeline that randomizes textures via domain randomization to focus on the shape information. In addition, we propose an RGB-D Fusion Mask R-CNN with a confidence map estimator, which exploits reliable depth information in multiple feature levels. We transferred the trained model to real-world scenarios and evaluated its performance by making comparisons with baselines and ablation studies. We demonstrate that our methods, which use only synthetic data, could be effective solutions for unseen industrial components segmentation.

Hogeon Seo, Seunghyeok Back, Seongju Lee et al.

A deep learning model, named IITNet, is proposed to learn intra- and inter-epoch temporal contexts from raw single-channel EEG for automatic sleep scoring. To classify the sleep stage from half-minute EEG, called an epoch, sleep experts investigate sleep-related events and consider the transition rules between the found events. Similarly, IITNet extracts representative features at a sub-epoch level by a residual neural network and captures intra- and inter-epoch temporal contexts from the sequence of the features via bidirectional LSTM. The performance was investigated for three datasets as the sequence length (L) increased from one to ten. IITNet achieved the comparable performance with other state-of-the-art results. The best accuracy, MF1, and Cohen's kappa ($κ$) were 83.9%, 77.6%, 0.78 for SleepEDF (L=10), 86.5%, 80.7%, 0.80 for MASS (L=9), and 86.7%, 79.8%, 0.81 for SHHS (L=10), respectively. Even though using four epochs, the performance was still comparable. Compared to using a single epoch, on average, accuracy and MF1 increased by 2.48%p and 4.90%p and F1 of N1, N2, and REM increased by 16.1%p, 1.50%p, and 6.42%p, respectively. Above four epochs, the performance improvement was not significant. The results support that considering the latest two-minute raw single-channel EEG can be a reasonable choice for sleep scoring via deep neural networks with efficiency and reliability. Furthermore, the experiments with the baselines showed that introducing intra-epoch temporal context learning with a deep residual network contributes to the improvement in the overall performance and has the positive synergy effect with the inter-epoch temporal context learning.