S
Shaopeng Guo
Researcher at SenseTime
Publications - 7
Citations - 292
Shaopeng Guo is an academic researcher from SenseTime. The author has contributed to research in topics: Differentiable function & Gradient descent. The author has an hindex of 3, co-authored 6 publications receiving 99 citations.
Papers
More filters
Posted Content
Incorporating Convolution Designs into Visual Transformers.
TL;DR: CeiT as discussed by the authors combines the advantages of CNNs in extracting low-level features, strengthening locality, and the advantage of Transformers in establishing long-range dependencies, which can reduce the training cost significantly.
Proceedings ArticleDOI
DMCP: Differentiable Markov Channel Pruning for Neural Networks
TL;DR: A novel differentiable method for channel pruning, named Differentiable Markov Channel Pruning (DMCP), to efficiently search the optimal sub-structure from unpruned networks, which can achieve consistent improvement than state-of-the-art pruning methods in various FLOPs settings.
Posted Content
DMCP: Differentiable Markov Channel Pruning for Neural Networks
TL;DR: Differentiable Markov Channel Pruning (DMCP) as mentioned in this paper is a differentiable channel pruning method that can be directly optimized by gradient descent with respect to standard task loss and budget regularization (e.g., FLOPs constraint).
Proceedings Article
Incorporating Convolution Designs Into Visual Transformers
TL;DR: CeiT as mentioned in this paper combines the advantages of CNNs in extracting low-level features, strengthening locality, and the advantage of Transformers in establishing long-range dependencies, which can reduce the training cost significantly.