Pith. sign in

REVIEW

Improving Ranking Correlation of Supernet with Candidates Enhancement and Progressive Training

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2108.05866 v1 pith:G5DF3FF3 submitted 2021-08-12 cs.CV

Improving Ranking Correlation of Supernet with Candidates Enhancement and Progressive Training

classification cs.CV
keywords supernetrankingarchitecturecandidatescorrelationenhancementmethodprogressive
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

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.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.