Fractional Skipping: Towards Finer-Grained Dynamic CNN Inference

By Jianghao Shen, Yonggan Fu, Yue Wang, Pengfei Xu, Zhangyang Wang, Yingyan Lin. 2020

49 citations recorded by the source corpus.

While increasingly deep networks are still in general desired for achieving state-of-the-art performance, for many specific inputs a simpler network might already suffice. Existing works exploited this observation by learning to skip convolutional layers in an input-dependent manner. However, we argue their binary decision scheme, i.e., either fully executing or completely bypassing one layer for a specific input, can be enhanced by introducing finer-grained, “softer” decisions. We therefore propose a Dynamic Fractional Skipping (DFS) framework. The core idea of DFS is to hypothesize layer-wise quantization (to different bitwidths) as intermediate “soft” choices to be made between fully utilizing and skipping a layer. For each input, DFS dynamically assigns a bitwidth to both weights and activations of each layer, where fully executing and skipping could be viewed as two “extremes” (i.e., full bitwidth and zero bitwidth). In this way, DFS can “fractionally” exploit a layer's expressive power during input-adaptive inference, enabling finer-grained accuracy-computational cost trade-offs. It presents a unified view to link input-adaptive layer skipping and input-adaptive hybrid quantization. Extensive experimental results demonstrate the superior tradeoff between computational cost and model expressive power (accuracy) achieved by DFS. More visualizations also indicate a smooth and consistent transition in the DFS behaviors, especially the learned choices between layer skipping and different quantizations when the total computational budgets vary, validating our hypothesis that layer quantization could be viewed as intermediate variants of layer skipping. Our source code and supplementary material are available at https://github.com/Torment123/DFS.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Efficiency & Compression

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Shiji Song
  2. Yulin Wang
  3. Gao Huang
  4. Le Yang
  5. Yizeng Han
  6. Honghui Wang
  7. Quoc V. Le
  8. Alan L. Yuille

In Computer Vision and Pattern Recognition

  1. Shiji Song
  2. Yulin Wang
  3. Gao Huang
  4. Yizeng Han
  5. Le Yang
  6. Honghui Wang
  7. Luc Van Gool
  8. Alan L. Yuille

In Efficiency & Compression

  1. Shiji Song
  2. Gao Huang
  3. Yulin Wang
  4. Le Yang
  5. Yizeng Han
  6. Honghui Wang

Citations in the corpus