Inseop Chung
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Inseop Chung has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Nojun Kwak
Seoul National University
6 shared publications - Jayeon Yoo
Seoul National University
2 shared publications Changki Sung
School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea
1 shared publicationDaeho Um
Department of Electrical and Computer Engineering, Automation and Systems Research Institute (ASRI), SNU, Seoul, Republic of Korea
1 shared publication- Daesik Kim
NAVER WEBTOON Corp Seongnam South Korea
1 shared publication Dasol Hong
School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea
1 shared publication
Latest Publications
- Open Access
- 25 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 150473-150488
Mitigating the Bias in the Model for Continual Test-Time Adaptation
Modern machine-learning models often encounter streams of new, unlabeled data whose appearance gradually changes over time after deployment—for example, vision models on autonomous vehicles facing day-to-night transitions, surveillance cameras experiencing seasonal lighting shifts, or medical scanners with hardware ageing effects. Continual Test-Time Adaptation (CTA) refers to methods that, once a model is deployed, adapt it online during test time without any labeled examples or prior notice of distribution shifts to maintain accuracy in changing environments. However, as the model adapts, it can become over-confident in its mistakes and steadily biased toward recent but unreliable patterns. In this work, we introduce a simple prototype-based correction mechanism that stabilizes adaptation and reduces prediction bias. We maintain a running, class-wise exponential moving average (EMA) of target-domain feature centroids (prototypes) only from samples on which the model is confident. During adaptation, we softly re-cluster incoming features around these target prototypes and at the same time align them with the source-domain prototypes learned offline. This dual clustering alignment step can be seamlessly integrated into existing CTA methods with almost no extra computation. We validate our approach on standard corruption benchmarks, ImageNet-C and CIFAR100-C. When integrated into a strong CTA baseline, our method raises classification accuracy by 1.51% points on ImageNet-C and by 1.47% points on CIFAR100-C in the most challenging corruption streams, demonstrating that prototype-guided clustering significantly curbs drift without slowing down adaptation.
- 25 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 150473-150488
Open AccessMitigating the Bias in the Model for Continual Test-Time Adaptation
Modern machine-learning models often encounter streams of new, unlabeled data whose appearance gradually changes over time after deployment—for example, vision models on autonomous vehicles facing day-to-night transitions, surveillance cameras experiencing seasonal lighting shifts, or medical scanners with hardware ageing effects. Continual Test-Time Adaptation (CTA) refers to methods that, once a model is deployed, adapt it online during test time without any labeled examples or prior notice of distribution shifts to maintain accuracy in changing environments. However, as the model adapts, it can become over-confident in its mistakes and steadily biased toward recent but unreliable patterns. In this work, we introduce a simple prototype-based correction mechanism that stabilizes adaptation and reduces prediction bias. We maintain a running, class-wise exponential moving average (EMA) of target-domain feature centroids (prototypes) only from samples on which the model is confident. During adaptation, we softly re-cluster incoming features around these target prototypes and at the same time align them with the source-domain prototypes learned offline. This dual clustering alignment step can be seamlessly integrated into existing CTA methods with almost no extra computation. We validate our approach on standard corruption benchmarks, ImageNet-C and CIFAR100-C. When integrated into a strong CTA baseline, our method raises classification accuracy by 1.51% points on ImageNet-C and by 1.47% points on CIFAR100-C in the most challenging corruption streams, demonstrating that prototype-guided clustering significantly curbs drift without slowing down adaptation.
- Open Access
Mitigating the Bias in the Model for Continual Test-Time Adaptation
Continual Test-Time Adaptation (CTA) is a challenging task that aims to adapt a source pre-trained model to continually changing target domains. In the CTA setting, a model does not know when the target domain changes, thus facing a drastic change in the distribution of streaming inputs during the test-time. The key challenge is to keep adapting the model to the continually changing target domains in an online manner. We find that a model shows highly biased predictions as it constantly adapts to the chaining distribution of the target data. It predicts certain classes more often than other classes, making inaccurate over-confident predictions. This paper mitigates this issue to improve performance in the CTA scenario. To alleviate the bias issue, we make class-wise exponential moving average target prototypes with reliable target samples and exploit them to cluster the target features class-wisely. Moreover, we aim to align the target distributions to the source distribution by anchoring the target feature to its corresponding source prototype. With extensive experiments, our proposed method achieves noteworthy performance gain when applied on top of existing CTA methods without substantial adaptation time overhead.
Open AccessMitigating the Bias in the Model for Continual Test-Time Adaptation
Continual Test-Time Adaptation (CTA) is a challenging task that aims to adapt a source pre-trained model to continually changing target domains. In the CTA setting, a model does not know when the target domain changes, thus facing a drastic change in the distribution of streaming inputs during the test-time. The key challenge is to keep adapting the model to the continually changing target domains in an online manner. We find that a model shows highly biased predictions as it constantly adapts to the chaining distribution of the target data. It predicts certain classes more often than other classes, making inaccurate over-confident predictions. This paper mitigates this issue to improve performance in the CTA scenario. To alleviate the bias issue, we make class-wise exponential moving average target prototypes with reliable target samples and exploit them to cluster the target features class-wisely. Moreover, we aim to align the target distributions to the source distribution by anchoring the target feature to its corresponding source prototype. With extensive experiments, our proposed method achieves noteworthy performance gain when applied on top of existing CTA methods without substantial adaptation time overhead.
- Open Access
End-to-End Multi-Object Detection with a Regularized Mixture Model
Recent end-to-end multi-object detectors simplify the inference pipeline by removing hand-crafted processes such as non-maximum suppression (NMS). However, during training, they still heavily rely on heuristics and hand-crafted processes which deteriorate the reliability of the predicted confidence score. In this paper, we propose a novel framework to train an end-to-end multi-object detector consisting of only two terms: negative log-likelihood (NLL) and a regularization term. In doing so, the multi-object detection problem is treated as density estimation of the ground truth bounding boxes utilizing a regularized mixture density model. The proposed \textit{end-to-end multi-object Detection with a Regularized Mixture Model} (D-RMM) is trained by minimizing the NLL with the proposed regularization term, maximum component maximization (MCM) loss, preventing duplicate predictions. Our method reduces the heuristics of the training process and improves the reliability of the predicted confidence score. Moreover, our D-RMM outperforms the previous end-to-end detectors on MS COCO dataset.
Open AccessEnd-to-End Multi-Object Detection with a Regularized Mixture Model
Recent end-to-end multi-object detectors simplify the inference pipeline by removing hand-crafted processes such as non-maximum suppression (NMS). However, during training, they still heavily rely on heuristics and hand-crafted processes which deteriorate the reliability of the predicted confidence score. In this paper, we propose a novel framework to train an end-to-end multi-object detector consisting of only two terms: negative log-likelihood (NLL) and a regularization term. In doing so, the multi-object detection problem is treated as density estimation of the ground truth bounding boxes utilizing a regularized mixture density model. The proposed \textit{end-to-end multi-object Detection with a Regularized Mixture Model} (D-RMM) is trained by minimizing the NLL with the proposed regularization term, maximum component maximization (MCM) loss, preventing duplicate predictions. Our method reduces the heuristics of the training process and improves the reliability of the predicted confidence score. Moreover, our D-RMM outperforms the previous end-to-end detectors on MS COCO dataset.
- 12 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 8 (2) , 1093-1100
X-MAS: Extremely Large-Scale Multi-Modal Sensor Dataset for Outdoor Surveillance in Real Environments
In robotics and computer vision communities, extensive studies have been widely conducted regarding surveillance tasks, including human detection, tracking, and motion recognition with a camera. Additionally, deep learning algorithms are widely utilized in the aforementioned tasks as in other computer vision tasks. Existing public datasets are insufficient to develop learning-based methods that handle various surveillance for outdoor and extreme situations such as harsh weather and low illuminance conditions. Therefore, we introduce a new large-scale outdoor surveillance dataset named e X tremely large-scale M ulti-mod A l S ensor dataset ( X-MAS ) containing more than 500,000 image pairs and the first-person view data annotated by well-trained annotators. Moreover, a single pair contains multi-modal data (e.g. an IR image, an RGB image, a thermal image, a depth image, and a LiDAR scan). This is the first large-scale first-person view outdoor multi-modal dataset focusing on surveillance tasks to the best of our knowledge. We present an overview of the proposed dataset with statistics and present methods of exploiting our dataset with deep learning-based algorithms.
- 12 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 8 (2) , 1093-1100
X-MAS: Extremely Large-Scale Multi-Modal Sensor Dataset for Outdoor Surveillance in Real Environments
In robotics and computer vision communities, extensive studies have been widely conducted regarding surveillance tasks, including human detection, tracking, and motion recognition with a camera. Additionally, deep learning algorithms are widely utilized in the aforementioned tasks as in other computer vision tasks. Existing public datasets are insufficient to develop learning-based methods that handle various surveillance for outdoor and extreme situations such as harsh weather and low illuminance conditions. Therefore, we introduce a new large-scale outdoor surveillance dataset named e X tremely large-scale M ulti-mod A l S ensor dataset ( X-MAS ) containing more than 500,000 image pairs and the first-person view data annotated by well-trained annotators. Moreover, a single pair contains multi-modal data (e.g. an IR image, an RGB image, a thermal image, a depth image, and a LiDAR scan). This is the first large-scale first-person view outdoor multi-modal dataset focusing on surveillance tasks to the best of our knowledge. We present an overview of the proposed dataset with statistics and present methods of exploiting our dataset with deep learning-based algorithms.
- 2 November 2022
- Published by Springer Nature
- p. 691-708
Unsupervised Domain Adaptation for One-Stage Object Detector Using Offsets to Bounding Box
- 2 November 2022
- Published by Springer Nature
- p. 691-708
Unsupervised Domain Adaptation for One-Stage Object Detector Using Offsets to Bounding Box
- Open Access
Maximizing Cosine Similarity Between Spatial Features for Unsupervised Domain Adaptation in Semantic Segmentation
We propose a novel method that tackles the problem of unsupervised domain adaptation for semantic segmentation by maximizing the cosine similarity between the source and the target domain at the feature level. A segmentation network mainly consists of two parts, a feature extractor and a classification head. We expect that if we can make the two domains have small domain gap at the feature level, they would also have small domain discrepancy at the classification head. Our method computes a cosine similarity matrix between the source feature map and the target feature map, then we maximize the elements exceeding a threshold to guide the target features to have high similarity with the most similar source feature. Moreover, we use a class-wise source feature dictionary which stores the latest features of the source domain to prevent the unmatching problem when computing the cosine similarity matrix and be able to compare a target feature with various source features from various images. Through extensive experiments, we verify that our method gains performance on two unsupervised domain adaptation tasks (GTA5$\to$ Cityscaspes and SYNTHIA$\to$ Cityscapes).
Open AccessMaximizing Cosine Similarity Between Spatial Features for Unsupervised Domain Adaptation in Semantic Segmentation
We propose a novel method that tackles the problem of unsupervised domain adaptation for semantic segmentation by maximizing the cosine similarity between the source and the target domain at the feature level. A segmentation network mainly consists of two parts, a feature extractor and a classification head. We expect that if we can make the two domains have small domain gap at the feature level, they would also have small domain discrepancy at the classification head. Our method computes a cosine similarity matrix between the source feature map and the target feature map, then we maximize the elements exceeding a threshold to guide the target features to have high similarity with the most similar source feature. Moreover, we use a class-wise source feature dictionary which stores the latest features of the source domain to prevent the unmatching problem when computing the cosine similarity matrix and be able to compare a target feature with various source features from various images. Through extensive experiments, we verify that our method gains performance on two unsupervised domain adaptation tasks (GTA5$\to$ Cityscaspes and SYNTHIA$\to$ Cityscapes).
- Open Access
Feature-map-level Online Adversarial Knowledge Distillation
Feature maps contain rich information about image intensity and spatial correlation. However, previous online knowledge distillation methods only utilize the class probabilities. Thus in this paper, we propose an online knowledge distillation method that transfers not only the knowledge of the class probabilities but also that of the feature map using the adversarial training framework. We train multiple networks simultaneously by employing discriminators to distinguish the feature map distributions of different networks. Each network has its corresponding discriminator which discriminates the feature map from its own as fake while classifying that of the other network as real. By training a network to fool the corresponding discriminator, it can learn the other network's feature map distribution. We show that our method performs better than the conventional direct alignment method such as L1 and is more suitable for online distillation. Also, we propose a novel cyclic learning scheme for training more than two networks together. We have applied our method to various network architectures on the classification task and discovered a significant improvement of performance especially in the case of training a pair of a small network and a large one.
Open AccessFeature-map-level Online Adversarial Knowledge Distillation
Feature maps contain rich information about image intensity and spatial correlation. However, previous online knowledge distillation methods only utilize the class probabilities. Thus in this paper, we propose an online knowledge distillation method that transfers not only the knowledge of the class probabilities but also that of the feature map using the adversarial training framework. We train multiple networks simultaneously by employing discriminators to distinguish the feature map distributions of different networks. Each network has its corresponding discriminator which discriminates the feature map from its own as fake while classifying that of the other network as real. By training a network to fool the corresponding discriminator, it can learn the other network's feature map distribution. We show that our method performs better than the conventional direct alignment method such as L1 and is more suitable for online distillation. Also, we propose a novel cyclic learning scheme for training more than two networks together. We have applied our method to various network architectures on the classification task and discovered a significant improvement of performance especially in the case of training a pair of a small network and a large one.