19 citations · 29 across the 4 of their papers we have counts for
4 papers
KernelWarehouse: Towards Parameter-Efficient Dynamic Convolution
Chao Li, Anbang Yao
Dynamic convolution learns a linear mixture of static kernels weighted with their sample-dependent attentions, demonstrating superior performance compared to normal convolution…
NORM: Knowledge Distillation via N-to-One Representation Matching
Xiaolong Liu, Lujun Li, Chao Li +1
Existing feature distillation methods commonly adopt the One-to-one Representation Matching between any pre-selected teacher-student layer pair. In this paper, we present N-to-One…
GMConv: Modulating Effective Receptive Fields for Convolutional Kernels
Qi Chen, Chao Li, Jia Ning +2
In convolutional neural networks, the convolutions are conventionally performed using a square kernel with a fixed N N receptive field (RF). However, what matters most to…
MAFormer: A Transformer Network with Multi-scale Attention Fusion for Visual Recognition
Yunhao Wang, Huixin Sun, Xiaodi Wang +6
Vision Transformer and its variants have demonstrated great potential in various computer vision tasks. But conventional vision transformers often focus on global dependency at a c…