Back to Search Start Over

Discriminability Distillation in Group Representation Learning

Authors :
Yu Liu
Guanglu Song
Manyuan Zhang
Hang Zhou
Source :
Computer Vision – ECCV 2020 ISBN: 9783030586065, ECCV (10)
Publication Year :
2020
Publisher :
Springer International Publishing, 2020.

Abstract

Learning group representation is a commonly concerned issue in tasks where the basic unit is a group, set, or sequence. Previously, the research community tries to tackle it by aggregating the elements in a group based on an indicator either defined by humans such as the quality and saliency, or generated by a black box such as the attention score. This article provides a more essential and explicable view. We claim the most significant indicator to show whether the group representation can be benefited from one of its element is not the quality or an inexplicable score, but the discriminability w.r.t. the model. We explicitly design the discrimiability using embedded class centroids on a proxy set. We show the discrimiability knowledge has good properties that can be distilled by a light-weight distillation network and can be generalized on the unseen target set. The whole procedure is denoted as discriminability distillation learning (DDL). The proposed DDL can be flexibly plugged into many group-based recognition tasks without influencing the original training procedures. Comprehensive experiments on various tasks have proven the effectiveness of DDL for both accuracy and efficiency. Moreover, it pushes forward the state-of-the-art results on these tasks by an impressive margin.

Details

ISBN :
978-3-030-58606-5
ISBNs :
9783030586065
Database :
OpenAIRE
Journal :
Computer Vision – ECCV 2020 ISBN: 9783030586065, ECCV (10)
Accession number :
edsair.doi...........c5a12b7a11cc853cfc213cdac6d4a273
Full Text :
https://doi.org/10.1007/978-3-030-58607-2_1