Attention-based dropout layer for weakly supervised object localization

Junsuk Choe, Hyunjung Shim

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

5 Citations (Scopus)

Abstract

Weakly Supervised Object Localization (WSOL) techniques learn the object location only using image-level labels, without location annotations. A common limitation for these techniques is that they cover only the most discriminative part of the object, not the entire object. To address this problem, we propose an Attention-based Dropout Layer (ADL), which utilizes the self-attention mechanism to process the feature maps of the model. The proposed method is composed of two key components: 1) hiding the most discriminative part from the model for capturing the integral extent of object, and 2) highlighting the informative region for improving the recognition power of the model. Based on extensive experiments, we demonstrate that the proposed method is effective to improve the accuracy of WSOL, achieving a new state-of-the-art localization accuracy in CUB-200-2011 dataset. We also show that the proposed method is much more efficient in terms of both parameter and computation overheads than existing techniques.

Original languageEnglish
Title of host publicationProceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
PublisherIEEE Computer Society
Pages2214-2223
Number of pages10
ISBN (Electronic)9781728132938
DOIs
Publication statusPublished - 2019 Jun
Event32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019 - Long Beach, United States
Duration: 2019 Jun 162019 Jun 20

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
CountryUnited States
CityLong Beach
Period19/6/1619/6/20

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Attention-based dropout layer for weakly supervised object localization'. Together they form a unique fingerprint.

  • Cite this

    Choe, J., & Shim, H. (2019). Attention-based dropout layer for weakly supervised object localization. In Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019 (pp. 2214-2223). [8954302] (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2019-June). IEEE Computer Society. https://doi.org/10.1109/CVPR.2019.00232