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

Efficient Online Subclass Knowledge Distillation for Image Classification

Tzelepi, Maria ; Passalis, Nikolaos ; Tefas, Anastasios

2020 25th International Conference on Pattern Recognition (ICPR), 2021, p.1007-1014

IEEE

Sem texto completo

Citações Citado por
  • Título:
    Efficient Online Subclass Knowledge Distillation for Image Classification
  • Autor: Tzelepi, Maria ; Passalis, Nikolaos ; Tefas, Anastasios
  • Assuntos: Computational modeling ; Deep learning ; Embedded systems ; Image classification ; Pattern recognition ; Rendering (computer graphics) ; Training
  • É parte de: 2020 25th International Conference on Pattern Recognition (ICPR), 2021, p.1007-1014
  • Descrição: Deploying state-of-the-art deep learning models on embedded systems dictates certain storage and computation limitations. During the recent few years Knowledge Distillation (KD) has been recognized as a prominent approach to address this issue. That is, KD has been effectively proposed for training fast and compact deep learning models by transferring knowledge from more complex and powerful models. However, knowledge distillation, in its conventional form, involves multiple stages of training, rendering it a computationally and memory demanding procedure. In this paper, a novel single-stage self knowledge distillation method is proposed, namely Online Subclass Knowledge Distillation (OSKD), that aims at revealing the similarities inside classes, so as to improve the performance of any deep neural model in an online manner. Hence, as opposed to existing online distillation methods, we are able to acquire further knowledge from the model itself, without building multiple identical models or using multiple models to teach each other, rendering the proposed OSKD approach more efficient. The experimental evaluation on two datasets validates that the proposed method improves the classification performance.
  • Editor: IEEE
  • Idioma: Inglês
Voltar para lista de resultados

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

Buscando em bases de dados remotas. Favor aguardar.