342 citations · 1.8k across the 90 of their papers we have counts for
Showing 2019Show all
3 papers · 1 filter
cs.CV2019★ 72 cited
Dynamic Convolution: Attention over Convolution Kernels
Yinpeng Chen, Xiyang Dai, Mengchen Liu +3
Light-weight convolutional neural networks (CNNs) suffer performance degradation as their low computational budgets constrain both the depth (number of convolution layers) and the…
cs.CV2019★ 2 cited
Large Scale Incremental Learning
Yue Wu, Yinpeng Chen, Lijuan Wang +4
Modern machine learning suffers from catastrophic forgetting when learning new classes incrementally. The performance dramatically degrades due to the missing data of old classes.…
cs.CV2019★ 40 cited
Rethinking Classification and Localization for Object Detection
Yue Wu, Yinpeng Chen, Lu Yuan +4
Two head structures (i.e. fully connected head and convolution head) have been widely used in R-CNN based detectors for classification and localization tasks. However, there is a l…