Dong Zhang (张冬)

Dong Zhang (张冬)

Research Assistant Professor

Publications

Memory Efficient Transformer Adapter
Memory Efficient Transformer Adapter for Dense Predictions

Dong Zhang, Rui Yan, Pingcheng Dong, Kwang-Ting Cheng.

International Conference on Learning Representations (ICLR), 2025.
Generalized Task-Driven Medical Image Quality Enhancement
Generalized Task-Driven Medical Image Quality Enhancement with Gradient Promotion

Dong Zhang, and Kwang-Ting Cheng.

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025.
CAE-GReaT
CAE-GReaT: Convolutional-Auxiliary Efficient Graph Reasoning Transformer for Dense Image Predictions

Dong Zhang, Yi Lin, Jinhui Tang, and Kwang-Ting Cheng.

International Journal of Computer Vision (IJCV), 2023.
Causal Intervention for Weakly-Supervised Semantic Segmentation
Causal Intervention for Weakly-Supervised Semantic Segmentation

Dong Zhang, Hanwang Zhang, Jinhui Tang, Xiansheng Hua, and Qianru Sun.

Advances in Neural Information Processing Systems (NeurIPS oral), 2020.
Feature Pyramid Transformer
Feature Pyramid Transformer

Dong Zhang, Hanwang Zhang, Jinhui Tang, Meng Wang, Xiansheng Hua, and Qianru Sun.

European Conference on Computer Vision (ECCV), 2020.

2025:

  • Dong Zhang, Lingfeng He, Rui Yan, Fei Shen, Jinhui Tang. R-Genie: Reasoning-Guided Generative Image Editing. arXiv, 2025.
  • Shu Jiang, Dong Zhang#, Rui Yan, Xiangbo Shu, Pingcheng Dong, Long Chen, Xiaoyu Du. Eliminating Semantic Ambiguity in Human Pose Estimation via Stable Feature Upsampling. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2025.
  • Chuhan Zhang, Chaoyang Zhu, Pingcheng Dong, Long Chen, Dong Zhang#. Cyclic Contrastive Knowledge Transfer for Open-Vocabulary Object Detection. International Conference on Learning Representations (ICLR), 2025.
  • Zenan Shi, Haipeng Chen, and Dong Zhang#. Robustifying Vision Transformer for Image Forgery Localization with Multi-Exit Architectures. Pattern Recognition (PR), 2025.
  • Zenan Shi, Haipeng Chen, Yixin Jia, Dong Zhang#, Wei Lu, Xun Yang. Customized Transformer Adapter with Frequency Masking for Deepfake Detection. IEEE Transactions on Information Forensics and Security (TIFS), 2025.
  • Yun Zhu, Dong Zhang#, Yi Lin, Yifei Feng, Jinhui Tang. Merging Context Clustering with Visual State Space Models for Medical Image Segmentation. IEEE Transactions on Medical Imaging (TMI), 2025.
  • Yu Quan, Dong Zhang, Jinhui Tang. Generalized Concordant Vision Transformer with Masked Image Tokens for Object Detection. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2025.
  • Dingwei Zhang, Dong Zhang, Jinhui Tang. Mitigating Query Selection Bias in Referring Video Object Segmentation. ACM International Conference on Multimedia (ACM MM), 2025.
  • Chunyan Wang, Dong Zhang, Jinhui Tang. Diffusion-Guided Knowledge Distillation for Weakly-Supervised Low-light Semantic Segmentation. ACM International Conference on Multimedia (ACM MM), 2025.
  • Haipeng Chen, Yixin Jia, Zenan Shi, Dong Zhang. ADNet: Delving into Generalizable Deepfake Detection via Adaptive Expert Selection and Discrepancy Learning. Pattern Recognition (PR), 2025.
  • Yi Lin, Dong Zhang, Yufan Chen, Hao Chen, and Kwang-Ting Cheng. Rethinking Boundary Detection in Deep Learning-Based Medical Image Segmentation. Medical Image Analysis (MedIA), 2025.
  • Xixi Jiang, Dong Zhang, Xiang Li, Kangyi Liu, Kwang-Ting Cheng, Xin Yang. Labeled-to-Unlabeled Distribution Alignment for Partially-Supervised Multi-Organ Medical Image Segmentation. Medical Image Analysis (MedIA), 2025.
  • Yuchen Shen, Dong Zhang, Zhao Zhang, Liyong Fu, Qiaolin Ye. Synthetic Instance Segmentation from Semantic Image Segmentation Masks. Knowledge-based Systems, 2025.
  • Qianhao Wu, Xixi Jiang, Dong Zhang#, Yifei Feng, Jinhui Tang. Cross-Set Data Augmentation for Semi-Supervised Medical Image Segmentation. Image and Vision Computing, 2025.
  • Yi Lin, Xiao Fang, Dong Zhang, Kwang-Ting Cheng, and Hao Chen. Boosting Convolution with Efficient MLP-Permutation for Volumetric Medical Image Segmentation. IEEE Transactions on Medical Imaging (TMI), 2025.
  • Rui Yan, Jin Wang, Hongyu Qu, Xiaoyu Du, Dong Zhang, Jinhui Tang, and Tieniu Tan. TEST-V: TEst-time Support-set Tuning for Zero-shot Video Classification. International Joint Conference on Artificial Intelligence (IJCAI), 2025.
  • Lin Li, Chuhan Zhang, Dong Zhang, Chong Sun, Chen Li, and Long Chen. Interaction-Centric Knowledge Infusion and Transfer for Open Vocabulary Scene Graph Generation. Advances in Neural Information Processing Systems (NeurIPS), 2025.
  • Yonghao Tan, Pingcheng Dong, Yongkun Wu, Yu Liu, Xuejiao Liu, Peng Luo, Shih-Yang Liu, Xijie Huang, Dong Zhang, Luhong Liang and Kwang-Ting Cheng. Additive Partial Sum Quantization with Algorithm-Hardware Co-Design. ACM/IEEE Design Automation Conference (DAC), 2025.
  • Pingcheng Dong, Yonghao Tan, Xuejiao Liu, Peng Luo, Yu Liu, Luhong Liang, Yitong Zhou, Di Pang, Manto Yung, Dong Zhang, Xijie Huang, Shih-Yang Liu, Yongkun Wu, Fengshi Tian, Chi-Ying Tsui, Fengbin Tu, Kwang-Ting Cheng. A 28nm 0.22μJ/Token Memory-Compute-Intensity-Aware CNN-Transformer Accelerator with Hybrid-Attention-Based Layer-Fusion and Cascaded Pruning for Semantic Segmentation. IEEE International Solid-State Circuits Conference (ISSCC The First Hong Kong AI Chip at ISSCC), 2025.

2024:

  • Dong Zhang, Pingcheng Dong, Long Chen, and Kwang-Ting Cheng. Towards Customized Knowledge Distillation for Efficient Dense Image Predictions, arXiv, 2024.
  • Hao Tang, Zechao Li, Dong Zhang, Shengfeng He, and Jinhui Tang. Divide-and-Conquer: Confluent Triple-Flow Network for RGB-T Salient Object Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024.
  • Shuhan Li, Dong Zhang, Xiaomeng Li, Chubin Ou, Lin An, Yanwu Xu, Weihua Yang, Yanchun Zhang, Kwang-Ting Cheng. Vessel-Promoted OCT to OCTA Image Translation by Heuristic Contextual Constraints. Medical Image Analysis (MedIA), 2024.
  • Chunyan Wang, Dong Zhang#, and Rui Yan. Boosting Weakly-Supervised Image Segmentation via Representation, Transform, and Compensator. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2024.
  • Peng Xing, Dong Zhang, Jinhui Tang, and Zechao Li. A Recover-then-Discriminate Framework for Robust Anomaly Detection. SCIENCE CHINA Information Sciences (SCIS), 2024.
  • Yangjun Mao, Jun Xiao, Dong Zhang, Meng Cao, Jian Shao, Yueting Zhuang, and Long Chen. Improving Reference-based Distinctive Image Captioning with Contrastive Rewards. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 2024.
  • Xiao Fang, Yi Lin, Dong Zhang, Kwang-Ting Cheng, and Hao Chen. Aligning Medical Images with General Knowledge from Large Language Models. Medical Image Computing and Computer Assisted Intervention (MICCAI Early Accept, Oral), 2024.
  • Fengyun Wang, Qianru Sun, Dong Zhang, and Jinhui Tang. Unleashing Network Potentials for Semantic Scene Completion. The IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2024.
  • Yi Lin, Zeyu Wang, Dong Zhang, Kwang-Ting Cheng, and Hao Chen. BoNuS: Boundary Mining for Nuclei Segmentation with Partial Point Labels. IEEE Transactions on Medical Imaging (TMI), 2024.
  • Qianhao Wu, Jiaxin Qi, Dong Zhang, Hanwang Zhang, Jinhui Tang. Fine-Tuning for Few-shot Image Classification by Multimodal Prototype Regularization. IEEE Transactions on Multimedia (TMM), 2024.
  • Pingcheng Dong, Yonghao Tan, Dong Zhang, Tianwei Ni, Xuejiao Liu, Yu Liu, Peng Luo, Luhong Liang, Shih-Yang Liu, Xijie Huang, Huaiyu Zhu, Yun Pan, Fengwei An, and Kwang-Ting Cheng. Genetic Quantization-Aware Approximation for Non-Linear Operations in Transformers. ACM/IEEE Design Automation Conference (DAC Oral), 2024.
  • Pingcheng Dong, Yonghao Tan, Dong Zhang, Yongkun Wu, Xijie Huang, Shih-Yang Liu, Yu Liu, Xuejiao Liu, Peng Luo, Luhong Liang, Fengwei An, and Kwang-Ting Cheng. Additive Partial Sum Quantization. ACM/IEEE Design Automation Conference (DAC), 2024.

2023:

  • Dong Zhang, Liyan Zhang, and Jinhui Tang. Augmented FCN: Rethinking Context Modeling for Semantic Segmentation. SCIENCE CHINA Information Sciences (SCIS), 2023.
  • Zenan Shi, Haipeng Chen, and Dong Zhang#. Transformer-Auxiliary Neural Networks for Image Manipulation Localization by Operator Inductions. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2023.
  • Zenan Shi, Haipeng Chen, Long Chen, and Dong Zhang#. Discrepancy-Guided Reconstruction Learning for Image Forgery Detection. International Joint Conference on Artificial Intelligence (IJCAI), 2023.
  • Dong Liang*, Dong Zhang*, Qiong Wang, Zongqi Wei, and Liyan Zhang. CrossNet: Cross-Scene Background Subtraction Network via 3D Optical Flow. IEEE Transactions on Multimedia (TMM), 2023.
  • Yi Lin*, Dong Zhang*, Xiao Fang, Yufan Chen, Kwang-Ting Cheng, and Hao Chen. Rethinking Boundary Detection in Deep Learning Models for Medical Image Segmentation. Information Processing in Medical Imaging (IPMI), 2023.
  • Chunyan Wang, Dong Zhang, Liyan Zhang, and Jinhui Tang. Coupling Global Context and Local Contents for Weakly-Supervised Semantic Segmentation. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2023.
  • Yu Quan, Dong Zhang, Liyan Zhang, and Jinhui Tang. Centralized Feature Pyramid for Object Detection. IEEE Transactions on Image Processing (TIP), 2023.
  • Fengyun Wang, Dong Zhang, Hanwang Zhang, Jinhui Tang, Qianru Sun. Semantic Scene Completion with Cleaner Self. The IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2023.
  • Jeffry Wicaksana, Zengqiang Yan, Dong Zhang, Xijie Huang, Huimin Wu, Xin Yang, and Kwang-Ting Cheng. FedMix: Mixed Supervised Federated Learning for Medical Image Segmentation. IEEE Transactions on Medical Imaging (TMI), 2023.
  • Yuchen Shen, Dong Zhang, Yuhui Zheng, Zechao Li, Liyong Fu, and Qiaolin Ye. Training-Free Instance Segmentation from Semantic Image Segmentation Masks. arXiv, 2023.
  • Yi Lin, Xiao Fang, Dong Zhang, Kwang-Ting Cheng, and Hao Chen. A Permutable Hybrid Network for Volumetric Medical Image Segmentation. IEEE Transactions on Medical Imaging (TMI), 2023.

2022 and before:

  • Dong Zhang, Jinhui Tang, and Kwang-Ting Cheng. Graph Reasoning Transformer for Image Parsing. ACM International Conference on Multimedia (ACM MM), 2022.
  • Dong Zhang, Chengting Zuo, Qianhao Wu, Liyong Fu, and Xinguang Xiang. Unabridged Adjacent Modulation for Clothing Parsing. Pattern Recognition (PR), 2022.
  • Dong Zhang, Yi Lin, Hao Chen, Zhuotao Tian, Xin Yang, Jinhui Tang, and Kwang-Ting Cheng. Understanding the Tricks of Deep Learning in Medical Image Segmentation: Challenges and Future Directions. arXiv, 2022.
  • Zenan Shi, Haipeng Chen, Dong Zhang, and Xuanjing Shen. Pretraining-Driven Multimodal Boundary Aware Vision Transformer. Journal of Software (in Chinese), 2022.
  • Yangjun Mao, Long Chen, Zhihong Jiang, Dong Zhang, Zhimeng Zhang, Jian Shao, and Jun Xiao. Rethinking the Reference-based Distinctive Image Captioning. ACM International Conference on Multimedia (ACM MM), 2022.
  • Dong Zhang, Hanwang Zhang, Jinhui Tang, Xiansheng Hua, and Qianru Sun. Self-Regulation for Semantic Segmentation. International Conference on Computer Vision (ICCV), 2021.
  • Liyong Fu*, Dong Zhang*, and Qiaolin Ye. Recurrent Thrifty Attention Network for Remote Sensing Scene Recognition. IEEE Transactions on Geoscience and Remote Sensing, 2020.
  • Long Chen, Chujie Lu, Siliang Tang, Jun Xiao, and Dong Zhang, et al. Rethinking the Bottom-Up Framework for Query-based Video Localization. Association for the Advancement of Artificial Intelligence (AAAI oral), 2020.
  • Wenxuan Zhang*, Dong Zhang*, and Xinguang Xiang. Cascaded and Dual: Discrimination Oriented Network for Brain Tumor Classification. Asian Conference on Machine Learning (ACML spotlight), 2019.
  • Dong Zhang, Nan Li, and Qiaolin Ye. Positional Context Aggregation Network for Remote Sensing Scene Classification. IEEE Geoscience and Remote Sensing Letters, 2019.
  • Dong Zhang, Yunlian Sun, Qiaolin Ye, and Jinhui Tang. Recursive Discriminative Subspace Learning with L1-norm Distance Constraint. IEEE Transactions on Cybernetics (TCYB), 2018.