Local to global learning: Gradually adding classes for training deep neural networks

Hao Cheng, Dongze Lian, Bowen Deng, Shenghua Gao, Tao Tan, Yanlin Geng

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

8 Citations (Scopus)

Abstract

We propose a new learning paradigm, Local to Global Learning (LGL), for Deep Neural Networks (DNNs) to improve the performance of classification problems. The core of LGL is to learn a DNN model from fewer categories (local) to more categories (global) gradually within the entire training set. LGL is most related to the Self-Paced Learning (SPL) algorithm but its formulation is different from SPL. SPL trains its data from simple to complex, while LGL from local to global. In this paper, we incorporate the idea of LGL into the learning objective of DNNs and explain why LGL works better from an information-theoretic perspective. Experiments on the toy data, CIFAR-10, CIFAR-100, and ImageNet dataset show that LGL outperforms the baseline and SPL-based algorithms.

Original languageEnglish
Title of host publicationProceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
PublisherIEEE Computer Society
Pages4743-4751
Number of pages9
ISBN (Electronic)9781728132938
DOIs
Publication statusPublished - Jun 2019
Externally publishedYes
Event32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019 - Long Beach, United States
Duration: 16 Jun 201920 Jun 2019

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume2019-June
ISSN (Print)1063-6919

Conference

Conference32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
Country/TerritoryUnited States
CityLong Beach
Period16/06/1920/06/19

Keywords

  • Computer Vision Theory
  • Deep Learning
  • Representation Learning
  • Statistical Learning

Fingerprint

Dive into the research topics of 'Local to global learning: Gradually adding classes for training deep neural networks'. Together they form a unique fingerprint.

Cite this