Minimizing supervision in multi-label categorization

Rajat, Munender Varshney, Pravendra Singh, Vinay P. Namboodiri

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Multiple categories of objects are present in most images. Treating this as a multi-class classification is not justified. We treat this as a multi-label classification problem. In this paper, we further aim to minimize the supervision required for providing supervision in multi-label classification. Specifically, we investigate an effective class of approaches that associate a weak localization with each category either in terms of the bounding box or segmentation mask. Doing so improves the accuracy of multi-label categorization. The approach we adopt is one of active learning, i.e., incrementally selecting a set of samples that need supervision based on the current model, obtaining supervision for these samples, retraining the model with the additional set of supervised samples and proceeding again to select the next set of samples. A crucial concern is the choice of the set of samples. In doing so, we provide a novel insight, and no specific measure succeeds in obtaining a consistently improved selection criterion. We, therefore, provide a selection criterion that consistently improves the overall baseline criterion by choosing the top k set of samples for a varied set of criteria. Using this criterion, we are able to show that we can retain more than 98% of the fully supervised performance with just 20% of samples (and more than 96% using 10%) of the dataset on PASCAL VOC 2007 and 2012. Also, our proposed approach consistently outperforms all other baseline metrics for all benchmark datasets and model combinations.

Original languageEnglish
Title of host publicationProceedings - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020
PublisherIEEE
Pages93-102
Number of pages10
ISBN (Electronic)9781728193601
DOIs
Publication statusPublished - 28 Jul 2020
Event2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020 - Virtual, Online, USA United States
Duration: 14 Jun 202019 Jun 2020

Publication series

NameIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Volume2020-June
ISSN (Print)2160-7508
ISSN (Electronic)2160-7516

Conference

Conference2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020
CountryUSA United States
CityVirtual, Online
Period14/06/2019/06/20

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this