Title | ||
---|---|---|
S2DNAS: Transforming Static CNN Model for Dynamic Inference via Neural Architecture Search |
Abstract | ||
---|---|---|
Recently, dynamic inference has emerged as a promising way to reduce the computational cost of deep convolutional neural networks (CNNs). In contrast to static methods (e.g., weight pruning), dynamic inference adaptively adjusts the inference process according to each input sample, which can considerably reduce the computational cost on “easy” samples while maintaining the overall model performance. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1007/978-3-030-58536-5_11 | European Conference on Computer Vision |
Keywords | DocType | Citations |
Dynamic inference,Neural architecture search,CNN | Conference | 0 |
PageRank | References | Authors |
0.34 | 0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yuan Zhihang | 1 | 0 | 0.34 |
Bingzhe Wu | 2 | 18 | 6.41 |
Guangyu Sun | 3 | 1920 | 111.55 |
Zheng Liang | 4 | 0 | 1.01 |
Shiwan Zhao | 5 | 318 | 17.41 |
Bi Weichen | 6 | 0 | 0.34 |