skip to main content
Idioma:
Primo Advanced Search
Primo Advanced Search Query Term
Primo Advanced Search prefilters
Busca Simples

Discretization-aware architecture search

Tian, Yunjie ; Liu, Chang ; Xie, Lingxi ; jiao, Jianbin ; Ye, Qixiang

Pattern recognition, 2021-12, Vol.120, p.108186, Article 108186 [Periódico revisado por pares]

Elsevier Ltd

Texto completo disponível

Citações Citado por
  • Título:
    Discretization-aware architecture search
  • Autor: Tian, Yunjie ; Liu, Chang ; Xie, Lingxi ; jiao, Jianbin ; Ye, Qixiang
  • Assuntos: Discretization-aware ; Imbalanced network configuration ; Neural architecture search ; Weight-sharing
  • É parte de: Pattern recognition, 2021-12, Vol.120, p.108186, Article 108186
  • Descrição: •We propose discretization-aware architecture search (DA2S), and target at pushing the super-network towards the configuration of desired topol- ogy. DA2S is implemented with an entropy-based loss term, which can be regularized to differentiable architecture search in a plug-and-play fashion.•The regularization for architecture search is controlled by elaborated continuation functions, so that discretization is adaptive to the dynamic change of edges and operations.•Experiments on standard image classification benchmarks demonstrate the effectiveness of our approach, in particular, under imbalanced network configurations that were not studied before. The search cost of neural architecture search (NAS) has been largely reduced by differentiable architecture search and weight-sharing methods. Such methods optimize a super-network with all possible edges and operations, and determine the optimal sub-network by discretization, i.e., pruning off operations/edges of small weights. However, the discretization process performed on either operations or edges incurs significant inaccuracy and thus the quality of the architecture is not guaranteed. In this paper, we propose discretization-aware architecture search (DA2S), and target at pushing the super-network towards the configuration of desired topology. DA2S is implemented with an entropy-based loss term, which can be regularized to differentiable architecture search in a plug-and-play fashion. The regularization is controlled by elaborated continuation functions, so that discretization is adaptive to the dynamic change of edges and operations. Experiments on standard image classification benchmarks demonstrate the effectiveness of our approach, in particular, under imbalanced network configurations that were not studied before. Code is available at github.com/sunsmarterjie/DAAS.
  • Editor: Elsevier Ltd
  • Idioma: Inglês
Voltar para lista de resultados
Ir para página anteriorAnterior Resultado  17 AvançarIr para próxima página

  • Realização: ABCD-USP USP   Logos de Redes Sociais: Freepik

Buscando em bases de dados remotas. Favor aguardar.