Jinwoo Jeong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jinwoo Jeong has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
- Sungjei Kim
School of Computer Science and Engineering, Korea University of Technology and Education (KOREATECH), Cheonan, South Korea
4 shared publications - Sang-Hyo Park
Kyungpook National University
3 shared publications - Chaewon Moon
Kyungpook National University, Daegu, Republic of Korea
2 shared publications - Ha-Eun Ahn
Department of Electronic Engineering, Kwangnwoon University, Seoul 01897, Korea
2 shared publications - Heejung Choi
School of Computer Science and Engineering, Kyungpook National University, Daegu, South Korea
2 shared publications - Hyeon-Cheol Moon
Intelligent Semiconductor Device Research Center, Korea Electronics Technology Institute, Seongnam-si, Republic of Korea
2 shared publications
Latest Publications
- Open Access
- 31 October 2026
- Published by Elsevier in ICT Express
LSAQ: Adaptive post-training quantization for vision-centric 3D object detection
- 31 October 2026
- Published by Elsevier in ICT Express
Open AccessLSAQ: Adaptive post-training quantization for vision-centric 3D object detection
- 20 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 33 (10709908) , 1801-1805
GQKD: Greedy Query Knowledge Distillation for Efficient 3D Instance Segmentation
3D instance segmentation is a fundamental component of various 3D scene understanding applications. Recent transformer-based approaches have achieved strong performance through query-driven decoding. however, their repeated multi-layer decoder architectures impose substantial computational overhead, motivating the need for model compression. In this work, we identify two key phenomena across decoder layers: object disappearance, where valid object queries vanish as decoding proceeds, and object degradation, where intermediate-layer predictions can be more reliable than final-layer outputs. Based on these observations, we propose Greedy Query Knowledge Distillation (GQKD), an effective distillation framework for lightweight 3D instance segmentation. GQKD constructs a pseudo-GT query set to supervise the student model by selecting the best true-positive query for each instance across multiple decoder layers, along with low-confidence negative teacher queries. This Pseudo-GT recovers high-quality object hypotheses lost during decoding and provides balanced supervision by supplementing recovered positives with low-confidence negatives. Experimental results on ScanNetV2 demonstrate that GQKD enables a student model with approximately 50% reduced decoder depth to achieve performance close to the teacher when used alone, and further improves results when combined with existing distillation strategies.
- 20 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 33 (10709908) , 1801-1805
GQKD: Greedy Query Knowledge Distillation for Efficient 3D Instance Segmentation
3D instance segmentation is a fundamental component of various 3D scene understanding applications. Recent transformer-based approaches have achieved strong performance through query-driven decoding. however, their repeated multi-layer decoder architectures impose substantial computational overhead, motivating the need for model compression. In this work, we identify two key phenomena across decoder layers: object disappearance, where valid object queries vanish as decoding proceeds, and object degradation, where intermediate-layer predictions can be more reliable than final-layer outputs. Based on these observations, we propose Greedy Query Knowledge Distillation (GQKD), an effective distillation framework for lightweight 3D instance segmentation. GQKD constructs a pseudo-GT query set to supervise the student model by selecting the best true-positive query for each instance across multiple decoder layers, along with low-confidence negative teacher queries. This Pseudo-GT recovers high-quality object hypotheses lost during decoding and provides balanced supervision by supplementing recovered positives with low-confidence negatives. Experimental results on ScanNetV2 demonstrate that GQKD enables a student model with approximately 50% reduced decoder depth to achieve performance close to the teacher when used alone, and further improves results when combined with existing distillation strategies.
- Open Access
- 31 January 2026
- Published by The Korean Institute of Broadcast and Media Engineers in Journal of Broadcast Engineering
- Vol. 31 (1) , 16-25
A Compressed Dataset and a Detection-Denoising Framework for Enhancing 3D Gaussian Splatting Rendering under Video and Image Compression
- 31 January 2026
- Published by The Korean Institute of Broadcast and Media Engineers in Journal of Broadcast Engineering
- Vol. 31 (1) , 16-25
Open AccessA Compressed Dataset and a Detection-Denoising Framework for Enhancing 3D Gaussian Splatting Rendering under Video and Image Compression
- Open Access
- 31 January 2026
- Published by The Korean Institute of Broadcast and Media Engineers in Journal of Broadcast Engineering
- Vol. 31 (1) , 2-15
Performance Analysis of VGGT with Denoising under Various Compression Levels in Lossy Compression
- 31 January 2026
- Published by The Korean Institute of Broadcast and Media Engineers in Journal of Broadcast Engineering
- Vol. 31 (1) , 2-15
Open AccessPerformance Analysis of VGGT with Denoising under Various Compression Levels in Lossy Compression
- 6 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28 (15209210) , 3135-3146
Compression Framework for Light 3D Scene Graph Generation via Pruning-as-Search and Distillation
3D scene graph generation (3DSGG), which involves classifying objects and predicates, is an emerging topic in 3D scene understanding. Recent studies leveraging graph neural networks (GNNs) have introduced sophisticated architectures that enhance classification performance. However, since GNNs serve as the core and constitute the majority of parameters in 3DSGG models, their computational demands substantially increase overall complexity, which makes it difficult to determine the optimal model capacity. In this paper, we propose the first compression framework for lightweight 3DSGG models, based on pruning-as-search and knowledge distillation. This framework integrates multiple strategies and modules. In phase 1, the framework identifies the optimal compression ratio through pruning-as-search. In phase 2, to mitigate the accuracy loss incurred during compression, we employ structured pruning and a novel knowledge distillation strategy that effectively transfers precise information from the teacher to the compressed model. Experimental results show that our approach reduces model size by more than half while improving classification accuracy. Code is available at https://github.com/hojunking/3DSGG-compression.
- 6 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28 (15209210) , 3135-3146
Compression Framework for Light 3D Scene Graph Generation via Pruning-as-Search and Distillation
3D scene graph generation (3DSGG), which involves classifying objects and predicates, is an emerging topic in 3D scene understanding. Recent studies leveraging graph neural networks (GNNs) have introduced sophisticated architectures that enhance classification performance. However, since GNNs serve as the core and constitute the majority of parameters in 3DSGG models, their computational demands substantially increase overall complexity, which makes it difficult to determine the optimal model capacity. In this paper, we propose the first compression framework for lightweight 3DSGG models, based on pruning-as-search and knowledge distillation. This framework integrates multiple strategies and modules. In phase 1, the framework identifies the optimal compression ratio through pruning-as-search. In phase 2, to mitigate the accuracy loss incurred during compression, we employ structured pruning and a novel knowledge distillation strategy that effectively transfers precise information from the teacher to the compressed model. Experimental results show that our approach reduces model size by more than half while improving classification accuracy. Code is available at https://github.com/hojunking/3DSGG-compression.
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 1
AWa: An Activation-Weight Distribution-aware Binarization Method for Large Language Models
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 1
Open AccessAWa: An Activation-Weight Distribution-aware Binarization Method for Large Language Models
- Open Access
- 28 May 2025
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 19 (8) , 1-9
YOLOv6+: simple and optimized object detection model for INT8 quantized inference on mobile devices
- 28 May 2025
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 19 (8) , 1-9
Open AccessYOLOv6+: simple and optimized object detection model for INT8 quantized inference on mobile devices
- 22 November 2024
- Published by Springer Nature
- p. 461-477
IAM-VFI : Interpolate Any Motion for Video Frame Interpolation with Motion Complexity Map
- 22 November 2024
- Published by Springer Nature
- p. 461-477
IAM-VFI : Interpolate Any Motion for Video Frame Interpolation with Motion Complexity Map
- Open Access
- 23 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 131885-131896
Feature-Domain Adaptive Contrastive Distillation for Efficient Single Image Super-Resolution
Convolutional neural network-based single image super-resolution (SISR) involves numerous parameters and high computational expenses to ensure improved performance, limiting its applicability in resource-constrained devices such as mobile phones. Knowledge distillation (KD), which transfers useful knowledge from a teacher network to a student network, has been investigated as a method to make networks more efficient in terms of performance. To this end, feature distillation (FD) has been utilized in KD to minimize the Euclidean distance-based loss of feature maps between teacher and student networks. However, this technique does not adequately consider the effective and meaningful delivery of knowledge from the teacher to the student network to improve the latter’s performance under given network capacity constraints. In this study, we propose a feature-domain adaptive contrastive distillation (FACD) method to train lightweight student SISR networks efficiently. We highlight the limitations of existing FD methods in terms of Euclidean distance-based loss, and propose a feature-domain contrastive loss, which causes student networks to learn richer information from the teacher’s representation in the feature domain. We also implement adaptive distillation that performs distillation selectively depending on the conditions of the training patches. Experimental results showed that the proposed FACD scheme improves student enhanced deep residual networks and residual channel attention networks not only in terms of the peak signal-to-noise ratio on all benchmark datasets and scales but also in terms of subjective image quality, compared to the conventional FD approaches. Code will be release at https://github.com/hcmoon0613/FACD.
- 23 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 131885-131896
Open AccessFeature-Domain Adaptive Contrastive Distillation for Efficient Single Image Super-Resolution
Convolutional neural network-based single image super-resolution (SISR) involves numerous parameters and high computational expenses to ensure improved performance, limiting its applicability in resource-constrained devices such as mobile phones. Knowledge distillation (KD), which transfers useful knowledge from a teacher network to a student network, has been investigated as a method to make networks more efficient in terms of performance. To this end, feature distillation (FD) has been utilized in KD to minimize the Euclidean distance-based loss of feature maps between teacher and student networks. However, this technique does not adequately consider the effective and meaningful delivery of knowledge from the teacher to the student network to improve the latter’s performance under given network capacity constraints. In this study, we propose a feature-domain adaptive contrastive distillation (FACD) method to train lightweight student SISR networks efficiently. We highlight the limitations of existing FD methods in terms of Euclidean distance-based loss, and propose a feature-domain contrastive loss, which causes student networks to learn richer information from the teacher’s representation in the feature domain. We also implement adaptive distillation that performs distillation selectively depending on the conditions of the training patches. Experimental results showed that the proposed FACD scheme improves student enhanced deep residual networks and residual channel attention networks not only in terms of the peak signal-to-noise ratio on all benchmark datasets and scales but also in terms of subjective image quality, compared to the conventional FD approaches. Code will be release at https://github.com/hcmoon0613/FACD.
- Open Access
- 13 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 71994-72006
Textural Detail Preservation Network for Video Frame Interpolation
The subjective image quality of the Video Frame Interpolation (VFI) result depends on whether image features such as edges, textures and blobs are preserved. With the development of deep learning, various algorithms have been proposed and the objective results of VFI have significantly improved. Moreover, perceptual loss has been used in a method that enhances subjective quality by preserving the features of the image, and as a result, the subjective quality is improved. Despite the quality enhancements achieved in VFI, no analysis has been performed to preserve specific features in the interpolated frames. Therefore, we conducted an analysis to preserve textural detail, such as film grain noise, which can represent the texture of an image, and weak textures, such as droplets or particles. Based on our analysis, we identify the importance of synthesis networks in textural detail preservation and propose an enhanced synthesis network, the Textural Detail Preservation Network (TDPNet). Furthermore, based on our analysis, we propose a Perceptual Training Method (PTM) to address the issue of degraded Peak Signal-to-Noise Ratio (PSNR) when simply applying perceptual loss and to preserve more textural detail. We also propose a Multi-scale Resolution Training Method (MRTM) to address the issue of poor performance when testing datasets with a resolution different from that of the training dataset. The experimental results of the proposed network was outperformed in LPIPS and DISTS on the Vimeo90K, HD, SNU-FILM and UVG datasets compared with the state-of-the-art VFI algorithms, and the subjective results were also outperformed. Furthermore, applying PTM improved PSNR results by an average of 0.293dB compared to simply applying perceptual loss.
- 13 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 71994-72006
Open AccessTextural Detail Preservation Network for Video Frame Interpolation
The subjective image quality of the Video Frame Interpolation (VFI) result depends on whether image features such as edges, textures and blobs are preserved. With the development of deep learning, various algorithms have been proposed and the objective results of VFI have significantly improved. Moreover, perceptual loss has been used in a method that enhances subjective quality by preserving the features of the image, and as a result, the subjective quality is improved. Despite the quality enhancements achieved in VFI, no analysis has been performed to preserve specific features in the interpolated frames. Therefore, we conducted an analysis to preserve textural detail, such as film grain noise, which can represent the texture of an image, and weak textures, such as droplets or particles. Based on our analysis, we identify the importance of synthesis networks in textural detail preservation and propose an enhanced synthesis network, the Textural Detail Preservation Network (TDPNet). Furthermore, based on our analysis, we propose a Perceptual Training Method (PTM) to address the issue of degraded Peak Signal-to-Noise Ratio (PSNR) when simply applying perceptual loss and to preserve more textural detail. We also propose a Multi-scale Resolution Training Method (MRTM) to address the issue of poor performance when testing datasets with a resolution different from that of the training dataset. The experimental results of the proposed network was outperformed in LPIPS and DISTS on the Vimeo90K, HD, SNU-FILM and UVG datasets compared with the state-of-the-art VFI algorithms, and the subjective results were also outperformed. Furthermore, applying PTM improved PSNR results by an average of 0.293dB compared to simply applying perceptual loss.