Improving Ranking Correlation of Supernet with Candidates Enhancement and Progressive Training
Not on the map. Why?
Abstract (arXiv)
One-shot neural architecture search (NAS) applies weight-sharing supernet to reduce the unaffordable computation overhead of automated architecture designing. However, the weight-sharing technique worsens the ranking consistency of performance due to the interferences between different candidate networks. To address this issue, we propose a candidates enhancement method and progressive training pipeline to improve the ranking correlation of supernet. Specifically, we carefully redesign the sub-networks in the supernet and map the original supernet to a new one of high capacity. In addition, we gradually add narrow branches of supernet to reduce the degree of weight sharing which effectively alleviates the mutual interference between sub-networks. Finally, our method ranks the 1st place in the Supernet Track of CVPR2021 1st Lightweight NAS Challenge.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 6 of its 7 references that are in the map. First posted on arXiv 12 Aug 2021.
Builds on
6 of 7 references.
References · 6
- 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 943
- 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 787
- 2019Single Path One-Shot Neural Architecture Search with Uniform Samplingcited by 414
- 2019FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Searchcited by 130
- 2019MnasFPN: Learning Latency-aware Pyramid Architecture for Object Detection on Mobile Devicescited by 18
- 2019SCARLET-NAS: Bridging the Gap between Stability and Scalability in Weight-sharing Neural Architecture Searchcited by 6
Built on by
Citing papers per year: 2022: 2.
2 papers.