publications

2024

  1. Can We Trust the Unlabeled Target Data? Towards Backdoor Attack and Defense on Model Adaptation
    Lijun Sheng, Jian Liang, Ran He, Zilei Wang, and Tieniu Tan
    arXiv preprint arXiv:2401.06030, 2024
  2. ICML
    Realistic Unsupervised CLIP Fine-tuning with Universal Entropy Optimization
    Jian Liang, Lijun Sheng, Zhengbo Wang, Ran He, and Tieniu Tan
    In Forty-first International Conference on Machine Learning , 2024
  3. IJCV
    Learning Spatiotemporal Inconsistency via Thumbnail Layout for Face Deepfake Detection
    Yuting Xu, Jian Liang, Lijun Sheng, and Xiao-Yu Zhang
    International Journal of Computer Vision, 2024
  4. ICLR
    A hard-to-beat baseline for training-free clip-based adaptation
    Zhengbo Wang, Jian Liang, Lijun Sheng, Ran He, Zilei Wang, and Tieniu Tan
    In ICLR , 2024

2023

  1. ICCV
    Adaptguard: Defending against universal attacks for model adaptation
    Lijun Sheng, Jian Liang, Ran He, Zilei Wang, and Tieniu Tan
    In Proceedings of the IEEE/CVF International Conference on Computer Vision , 2023
  2. NN
    Proxymix: Proxy-based mixup training with label refinery for source-free domain adaptation
    Yuhe Ding, Lijun Sheng, Jian Liang, Aihua Zheng, and Ran He
    Neural Networks, 2023
  3. ICCVW
    Self-training solutions for the ICCV 2023 GeoNet Challenge
    Lijun Sheng, Zhengbo Wang, and Jian Liang
    arXiv preprint arXiv:2311.16843, 2023
  4. Unleashing the power of Neural Collapse for Transferability Estimation
    Yuhe Ding, Bo Jiang, Lijun Sheng, Aihua Zheng, and Jian Liang
    arXiv preprint arXiv:2310.05754, 2023
  5. Benchmarking test-time adaptation against distribution shifts in image classification
    Yongcan Yu, Lijun Sheng, Ran He, and Jian Liang
    arXiv preprint arXiv:2307.03133, 2023