skip to main content
Idioma:
Primo Search
Clear Search Box
Search in: Busca Geral
Busca Avançada
Busca por Índices

Are Labels Necessary for Neural Architecture Search?

Liu, Chenxi ; Dollár, Piotr ; He, Kaiming ; Girshick, Ross ; Yuille, Alan ; Xie, Saining

Computer Vision - ECCV 2020, 2020, Vol.12349, p.798-813 [Periódico revisado por pares]

Switzerland: Springer International Publishing AG

Sem texto completo

Citações Citado por
  • Título:
    Are Labels Necessary for Neural Architecture Search?
  • Autor: Liu, Chenxi ; Dollár, Piotr ; He, Kaiming ; Girshick, Ross ; Yuille, Alan ; Xie, Saining
  • Assuntos: Neural architecture search ; Unsupervised learning
  • É parte de: Computer Vision - ECCV 2020, 2020, Vol.12349, p.798-813
  • Notas: Electronic supplementary materialThe online version of this chapter (https://doi.org/10.1007/978-3-030-58548-8_46) contains supplementary material, which is available to authorized users.
  • Descrição: Existing neural network architectures in computer vision—whether designed by humans or by machines—were typically found using both images and their associated labels. In this paper, we ask the question: can we find high-quality neural architectures using only images, but no human-annotated labels? To answer this question, we first define a new setup called Unsupervised Neural Architecture Search (UnNAS). We then conduct two sets of experiments. In sample-based experiments, we train a large number (500) of diverse architectures with either supervised or unsupervised objectives, and find that the architecture rankings produced with and without labels are highly correlated. In search-based experiments, we run a well-established NAS algorithm (DARTS) using various unsupervised objectives, and report that the architectures searched without labels can be competitive to their counterparts searched with labels. Together, these results reveal the potentially surprising finding that labels are not necessary, and the image statistics alone may be sufficient to identify good neural architectures.
  • Títulos relacionados: Lecture Notes in Computer Science
  • Editor: Switzerland: Springer International Publishing AG
  • Idioma: Inglês
Voltar para lista de resultados

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

Buscando em bases de dados remotas. Favor aguardar.