An end-to-end approach for speeding up neural network inference

By Charles Herrmann, Richard Strong Bowen, Ramin Zabih. 2018

5 citations recorded by the source corpus.

Subfields: Model Architectures, Optimization & Training

How researchers see this paper

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

In Model Architectures

1. Zheng Zhang
2. Shiji Song
3. Gao Huang
4. Stephen Lin
5. Zhenda Xie
6. Xizhou Zhu
7. Yulin Wang
8. Honghui Wang

In Optimization & Training

1. Shiji Song
2. Yulin Wang
3. Le Yang
4. Gao Huang
5. Stephen Lin
6. Zhenda Xie
7. Honghui Wang
8. Zheng Zhang

Citations in the corpus

• Dynamic Neural Networks: A Survey (2021, methodology): “The gating functions take in intermediate features and efficiently produce binary-valued gate vectors to decide: 1) which channels need to be activated [15], [81], [82], [83], [84], 2) which layers need to be skipped [45], [46], [85], [86], 3) which paths should be selected in a SuperNet [101], or 4”
• Continual Object Detection via Prototypical Task Correlation Guided Gating Mechanism (2022, unknown): “It has been generally used to choose over different channels in dynamic pruning methods [4,8,10,13,19,21,29] and dynamic slimmable network [25].”
• Spatially Adaptive Inference with Stochastic Feature Sampling and Interpolation (2020, methodology): “The Gumbel-Softmax trick was utilized in adaptively choosing network layers to apply on an input image [33] and in selecting channels or layers to skip [14].”