40 citations · 157 across the 30 of their papers we have counts for
Showing 2022Show all
2 papers · 1 filter
cs.CV2022★ 11 cited
Latency-aware Spatial-wise Dynamic Networks
Yizeng Han, Zhihang Yuan, Yifan Pu +4
Spatial-wise dynamic convolution has become a promising approach to improving the inference efficiency of deep networks. By allocating more computation to the most informative pixe…
cs.CV2022★ 2 cited
Learning to Weight Samples for Dynamic Early-exiting Networks
Yizeng Han, Yifan Pu, Zihang Lai +6
Early exiting is an effective paradigm for improving the inference efficiency of deep networks. By constructing classifiers with varying resource demands (the exits), such networks…