40 citations · 117 across the 7 of their papers we have counts for
Showing 2020Show all
2 papers · 1 filter
cs.CV2020★ 29 cited
Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification
Yulin Wang, Kangchen Lv, Rui Huang +3
The accuracy of deep convolutional neural networks (CNNs) generally improves when fueled with high resolution images. However, this often comes at a high computational cost and hig…
cs.CV2020★ 22 cited
Resolution Adaptive Networks for Efficient Inference
Le Yang, Yizeng Han, Xi Chen +3
Adaptive inference is an effective mechanism to achieve a dynamic tradeoff between accuracy and computational cost in deep networks. Existing works mainly exploit architecture redu…