Jinhong Deng - SCSE

Home
Publications
Honors & Awards
Skills

Jinhong Deng

Ph.D. Student at SCSE, UESTC ; Visiting Student at A*STAR CFAR

I am currently a Ph.D student in the School of Computer Science and Engineering, University of Electronic Science and Technology of China (SCSE, UESTC), supervised by Prof. Lixin Duan and Prof. Wen Li. Before that, I obtained the B.Eng degree from the School of Information Science and Technology, Southwest Jiaotong University (SIST, SWJTU) in 2019.
Now, I am also a visiting student in A*STAR Centre for Frontier AI Research (CFAR), Singapore, supervised by Joey Tianyi Zhou and Yang He.

Email: jhdengvision AT gmail.com, [Google Scholar], [GitHub].

My general research interest lies in building a robust visual system capable of effectively operating in dynamic, open environments, with a particular focus on object detection. By addressing these challenges, my research aims to improve the performance, adaptability, and practicality of visual systems in real-world applications. Specifically, my research interests include:

Open-World Visual Understanding: Domain Adaptation for Object Detection/Segmentation, Open-Vocabulary Object Detection/Segmentation, etc.
Efficient Learning: Label-Efficient Learning, Data-Efficient Learning, etc.
Vision and Language Models, Multimedia Large Language Models, etc.

Updates

2025.03: Our work "ResCLIP: Residual Attention for Training-free Dense Vision-language Inference" has been accepted by CVPR 2025. Congrats to Yuhang.
2024.12: Our new work "Segmenting Anything in the Dark via Depth Perception" has been accepted by IEEE Transactions on Multimedia, 2024. Congrats to my bro Dr. Peng Liu.
2024.11: Our new work "ResCLIP: Residual Attention for Training-free Dense Vision-language Inference" has been released.
2024.09: One paper about unsupervised model selection for domain adaptive object detection has been accepted by NeurIPS, 2024.
2024.06: Very glad to attend the Doctoral Consortium at The 2024 IEEE Conference on Artificial Intelligence in Singapore and give a presentation about my researchs titled "Robust Object Detection in Open Environments."
2024.03: One paper has been accepted by TCSVT, 2024.
2024.02: One paper has been accepted by IEEE Transactions on Automation Science and Engineering, 2024.
2023.11: One paper has been accepted by IEEE Transactions on Multimedia, 2023.
2023.03: One paper has been accepted by CVPR 2023.
2022.06: One paper has been accepted by ECCV 2022.
2022.03: Two papers have been accepted by CVPR 2022.
2022.03: Serve as a reviewer for ECCV 2022.
2021.12: Our paper on source free domain adaptation has been accepted by AAAI 2022 for oral presentation.
2021.11: Serve as a reviewer for CVPR 2022.
2021.07: Our paper on cross-domain semantic segmentation has been accepted by ICCV 2021 for oral presentation.
2021.09: I start my Ph.D study at SCSE, UESTC.
2021.03: Our paper on cross-domain object detection is accepted by CVPR 2021.
2019.09: I start my Master study at SCSE, UESTC.

Publications

ResCLIP: Residual Attention for Training-free Dense Vision-language Inference

Yuhang Yang*, Jinhong Deng*, Wen Li, Lixin Duan. * equal contribution.

CVPR 2025.

[paper][code]

Towards Unsupervised Model Selection for Domain Adaptive Object Detection

Hengfu Yu*, Jinhong Deng*, Wen Li, Lixin Duan. * equal contribution.

Neural Information Processing Systems (NeurIPS), 2024.

[paper][code]

Balanced Teacher for Source-free Object Detection

Jinhong Deng, Wen Li, Lixin Duan.

IEEE Transactions on Circuits and Systems for Video Technology, 2024.

[paper]

Domain Adaptive Detection of MAVs: A Benchmark and Noise Suppression Network

Yin Zhang, Jinhong Deng, Peidong Liu, Wen Li, Shiyu Zhao.

IEEE Transactions on Automation Science and Engineering, 2024.

[paper]

Cross-domain Detection Transformer based on Spatial-aware and Semantic-aware Token Alignment

Jinhong Deng, Xiaoyue Zhang, Wen Li, Lixin Duan, Dong Xu.

IEEE Transactions on Multimedia, 2023.

[paper]

	Harmonious Teacher for Cross-domain Object Detection CVPR 2023 Jinhong Deng, Dongli Xu, Wen Li, Lixin Duan. [paper] [code]
	Motion and Appearance Adaptation for Cross-Domain Motion Transfer ECCV 2022 Borun Xu, Biao Wang, Jinhong Deng, Jiale Tao, Tiezheng Ge, Yuning Jiang, Wen Li, Lixin Duan. [paper]
	Undoing the Damage of Label Shift for Cross-domain Semantic Segmentation CVPR 2022 Yahao Liu, Jinhong Deng, Jiale Tao, Tong Chu, Lixin Duan, Wen Li. [paper] [code]
	Revisiting AP Loss for Dense Object Detection: Adaptive Ranking Pair Selection CVPR 2022 Dongli Xu, Jinhong Deng, Wen Li. [paper] [code]
	Denoised Maximum Classifier Discrepancy for Source-Free Unsupervised Domain Adaptation AAAI 2022 Tongchu, Yahao Liu, Jinhong Deng, Wen Li, Lixin Duan. Accepted as oral paper [paper]
	BAPA-Net: Boundary Adaptation and Prototype Alignment for Cross-domain Semantic Segmentation ICCV 2021 Yahao Liu, Jinhong Deng, Xinchen Gao, Wen Li, Lixin Duan. Accepted as oral paper [paper] [code]
	Unbiased Mean Teacher for Cross-domain Object Detection CVPR 2021 Jinhong Deng, Wen Li, Yuhua Chen, Lixin Duan. CVPR 2021 We propose an unbiased mean teacher method to improve the cross-domain ability of Faster RCNN. [paper] [code]

Experiences

	2024.09—Now: Visiting Ph.D. Student, A*STAR Centre for Frontier AI Research (CFAR)
	2021.09—Now: Ph.D student at SCSE, UESTC
	2019.09—2021.05: Master student at SCSE, UESTC
	2015.09—2019.05: Undergraduate student at Southwest Jiaotong University

Honors & Awards

2024, UESTC Academic Rising Star Award, UESTC.

2021, UESTC Academic Promising Talent Award, UESTC.

2019, The First Prize Graduate Academic Scholarships, UESTC.

2019, Outstanding graduates from Southwest Jiaotong University.

2019, TOP 10, SCADA Data Missing Repair Competition.

2019, TOP 3, AI Challenger 2018 in Weather Forecasting.

2017, National First Prize, 3Chuang: Innovation, Creativity, Entrepreneurship Competition.

2017, Third Prize, ACM Competition of Southwest Jiaotong University.

2016, 2017, National Encouragement scholarship, SWJTU.

Professional Activities

Conference Review

Journal Review

Skills

Programming: Python, LaTex, C/C++, Java
Framework: Pytorch
Languages: English(CET-6 565), Chinese(native speaker)
Hobbies and Interests: Swimming, Badminton, Books

Misc

Friends: Dongli Xu.
This template is from kelei.
Update: 2024.12