Skip to main content

and
  1. No Access

    Article

    Dynamic connection pruning for densely connected convolutional neural networks

    Densely connected convolutional neural networks dominate in a variety of downstream tasks due to their extraordinary performance. However, such networks typically require excessive computing resources, which h...

    **nyi Hu, Hangxiang Fang, Ling Zhang, Xue Zhang, Howard H. Yang in Applied Intelligence (2023)

  2. No Access

    Chapter and Conference Paper

    Towards Calibrated Hyper-Sphere Representation via Distribution Overlap Coefficient for Long-Tailed Learning

    Long-tailed learning aims to tackle the crucial challenge that head classes dominate the training procedure under severe class imbalance in real-world scenarios. However, little attention has been given to how...

    Hualiang Wang, Siming Fu, **aoxuan He, Hangxiang Fang in Computer Vision – ECCV 2022 (2022)