Second-Order Estimation Based Attention Network for Metric Learning

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

Abstract

Mapping image data into the embedding space where objects of the same class or label have a short distance in-between and objects of different classes have long margins, has been an essential task for many computer vision applications. However, current approaches struggle to map image data into a proper embedding space due to the difficulty of constructing discriminative features from among numerous features from the original data. Existing approaches include finding effective loss and new sampling methods, which do not consider improving the embedding space by selecting fine features extracted by the network. In this work, we proposed a new attention approach by exploiting the variance of features. The method can improve the performance of the current metric learning. Our approach consists of a variance estimation module(VEM) and fusion stage for applying channel-wise attention on extracted features. It is easy to implement and fast for training. Unlike other traditional second-order based methods, the variance estimation module does not embed second-order calculation in the network itself, and cost no large extra computation time in the evaluation stage. The experiment shows promising performance while compared with current SOTA approaches on multiple metric learning benchmark datasets such as CUB200-2011, CARS196, In-shop Clothes. Contribution-We design a new attention module by using estimation of variance in the features and achieve SOTA results in several benchmarks with almost no extra time cost in the test stage.

Original languageEnglish
Title of host publication2020 Joint 9th International Conference on Informatics, Electronics and Vision and 2020 4th International Conference on Imaging, Vision and Pattern Recognition, ICIEV and icIVPR 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728193311
DOIs
Publication statusPublished - 2020 Aug 26
EventJoint 9th International Conference on Informatics, Electronics and Vision and 4th International Conference on Imaging, Vision and Pattern Recognition, ICIEV and icIVPR 2020 - Kitakyushu, Japan
Duration: 2020 Aug 262020 Aug 29

Publication series

Name2020 Joint 9th International Conference on Informatics, Electronics and Vision and 2020 4th International Conference on Imaging, Vision and Pattern Recognition, ICIEV and icIVPR 2020

Conference

ConferenceJoint 9th International Conference on Informatics, Electronics and Vision and 4th International Conference on Imaging, Vision and Pattern Recognition, ICIEV and icIVPR 2020
CountryJapan
CityKitakyushu
Period20/8/2620/8/29

Keywords

  • Attention
  • Second-order Statistics

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Information Systems
  • Electrical and Electronic Engineering
  • Instrumentation

Fingerprint Dive into the research topics of 'Second-Order Estimation Based Attention Network for Metric Learning'. Together they form a unique fingerprint.

Cite this