Siamese transformer networks for few-shot image classification.

Shuoxi Zhang

Weihao Jiang Shuoxi Zhang Kun He 0001 Siamese transformer networks for few-shot image classification. 2026 114966 194 Appl. Soft Comput. https://doi.org/10.1016/j.asoc.2026.114966 db/journals/asc/asc194.html#JiangZH26 streams/journals/asc

Hanpeng Liu Shuoxi Zhang Kaiyuan Gao Kun He 0001 Boosting the patch-based self-supervised learning through past-to-present smoothing. 112871 2026 173 Pattern Recognit. https://doi.org/10.1016/j.patcog.2025.112871 db/journals/pr/pr173.html#LiuZGH26 streams/journals/pr

Hanpeng Liu Yaqian Li Zidan Wang Shuoxi Zhang Zihao Bo Rinyoichi Takezoe Kaiwen Long Kun He 0001 iGVLM: Dynamic Instruction-Guided Vision Encoding for Question-Aware Multimodal Understanding. 2026 March abs/2603.02748 CoRR https://doi.org/10.48550/arXiv.2603.02748 db/journals/corr/corr2603.html#abs-2603-02748 streams/journals/corr

Hanpeng Liu Yaqian Li Zidan Wang Shuoxi Zhang Zonglin Zhao Zihao Bo Rinyoichi Takezoe Kaiwen Long Kun He ITO: Images and Texts as One via Synergizing Multiple Alignment and Training-Time Fusion. 2026 March abs/2603.02767 CoRR https://doi.org/10.48550/arXiv.2603.02767 db/journals/corr/corr2603.html#abs-2603-02767 streams/journals/corr

Hanpeng Liu Zidan Wang Shuoxi Zhang Kaiyuan Gao Kun He 0001 Separators in Enhancing Autoregressive Pretraining for Vision Mamba. 2026 March abs/2603.03806 CoRR https://doi.org/10.48550/arXiv.2603.03806 db/journals/corr/corr2603.html#abs-2603-03806 streams/journals/corr

Hanpeng Liu Shuoxi Zhang Kun He 0001 Residual Learning for Self-Knowledge Distillation: Enhancing Neural Networks Through Consistency Across Layers. 2615-2627 2025 October 11 IEEE Trans. Big Data 5 https://doi.org/10.1109/TBDATA.2025.3552326 db/journals/tbd/tbd11.html#LiuZH25 streams/journals/tbd

Shuoxi Zhang Hanpeng Liu Yuyi Wang 0001 Kun He 0001 Jun Lin 0005 Yang Zeng Class Discriminative Knowledge Distillation. 1340-1351 2025 April 9 IEEE Trans. Emerg. Top. Comput. Intell. 2 https://doi.org/10.1109/TETCI.2025.3529896 db/journals/tetci/tetci9.html#ZhangLWHLZ25 streams/journals/tetci

Shuoxi Zhang Zijian Song Kun He 0001 Neural Collapse Inspired Knowledge Distillation. 22542-22550 2025 AAAI https://doi.org/10.1609/aaai.v39i21.34412 conf/aaai/2025 db/conf/aaai/aaai2025.html#ZhangS025 Shuoxi Zhang Hanpeng Liu Stephen Lin 0001 Kun He 0001 Hyperspherical Dataset Distillation via Contrastive Embedding Alignment. 1-6 2025 ICME https://doi.org/10.1109/ICME59968.2025.11208901 conf/icmcs/2025 db/conf/icmcs/icme2025.html#ZhangLLH25 streams/conf/icmcs

Kun He 0001 Zijian Song Shuoxi Zhang John E. Hopcroft Enhancing Pre-Trained Model-Based Class-Incremental Learning through Neural Collapse. 2025 April abs/2504.18437 CoRR https://doi.org/10.48550/arXiv.2504.18437 db/journals/corr/corr2504.html#abs-2504-18437 streams/journals/corr

Shuoxi Zhang Hanpeng Liu Kun He 0001 Knowledge Distillation via Token-Level Relationship Graph Based on the Big Data Technologies. 100438 2024 36 Big Data Res. https://doi.org/10.1016/j.bdr.2024.100438 db/journals/bdr/bdr36.html#ZhangLH24 streams/journals/bdr

Shuoxi Zhang Hanpeng Liu Stephen Lin 0001 Kun He 0001 You Only Need Less Attention at Each Stage in Vision Transformers. 6057-6066 2024 CVPR https://doi.org/10.1109/CVPR52733.2024.00579 conf/cvpr/2024 db/conf/cvpr/cvpr2024.html#ZhangL0024 Shuoxi Zhang Hanpeng Liu Yuyi Wang 0001 Kun He 0001 Grouped Logit Distillation Enhanced with Superclass Awareness for Efficient Knowledge Transfer. 2564-2571 2024 ECAI https://doi.org/10.3233/FAIA240786 conf/ecai/2024 db/conf/ecai/ecai2024.html#ZhangL0024

Shuoxi Zhang Hanpeng Liu Stephen Lin 0001 Kun He 0001 You Only Need Less Attention at Each Stage in Vision Transformers. 2024 abs/2406.00427 CoRR https://doi.org/10.48550/arXiv.2406.00427 db/journals/corr/corr2406.html#abs-2406-00427

Weihao Jiang Shuoxi Zhang Kun He 0001 Siamese Transformer Networks for Few-shot Image Classification. 2024 abs/2408.01427 CoRR https://doi.org/10.48550/arXiv.2408.01427 db/journals/corr/corr2408.html#abs-2408-01427 streams/journals/corr

Shuoxi Zhang Zijian Song Kun He 0001 Neural Collapse Inspired Knowledge Distillation. 2024 abs/2412.11788 CoRR https://doi.org/10.48550/arXiv.2412.11788 db/journals/corr/corr2412.html#abs-2412-11788 streams/journals/corr

Guodong Liu Tongling Wang Shuoxi Zhang Kun He 0001 Generating Pseudo-labels Adaptively for Few-shot Model-Agnostic Meta-Learning. 292-294 2023 BMVC http://proceedings.bmvc2023.org/292/ conf/bmvc/2023 db/conf/bmvc/bmvc2023.html#LiuWZ023

Shuoxi Zhang Hanpeng Liu Kun He 0001 Knowledge Distillation via Token-level Relationship Graph. 2023 abs/2306.12442 CoRR https://doi.org/10.48550/arXiv.2306.12442 db/journals/corr/corr2306.html#abs-2306-12442

Guodong Liu Tongling Wang Shuoxi Zhang Kun He 0001 Generating Pseudo-labels Adaptively for Few-shot Model-Agnostic Meta-Learning. 2022 abs/2207.04217 CoRR https://doi.org/10.48550/arXiv.2207.04217 db/journals/corr/corr2207.html#abs-2207-04217

Shuoxi Zhang Hanpeng Liu John E. Hopcroft Kun He 0001 Class-aware Information for Logit-based Knowledge Distillation. 2022 abs/2211.14773 CoRR https://doi.org/10.48550/arXiv.2211.14773 db/journals/corr/corr2211.html#abs-2211-14773

Zihao Bo Kaiyuan Gao Kun He Kun He 0001 John E. Hopcroft Weihao Jiang Yaqian Li Jun Lin 0005 Stephen Lin 0001 Guodong Liu Hanpeng Liu Kaiwen Long Zijian Song Rinyoichi Takezoe Tongling Wang Yuyi Wang 0001 Zidan Wang Yang Zeng Zonglin Zhao