A Tale of Two Losses: Discriminative Deep Feature Learning for Person Re-Identification

Alessandro Borgia, Yang Hua, Neil Robertson

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

55 Downloads (Pure)

Abstract

The changing camera viewpoint on full-body pedestrians in a multi-camera scenario may be problematic to handle, above all if the fields of view are non-overlapping. A direct effect of the viewpoint variability is that a pair of images of the same person shot by different cameras may appear to be more distant from each other in the feature space than one of them from an image of a different identity captured by the same camera. In order to tackle this problem, we propose to train a state-of-the-art CNN by two new loss functions that jointly increase the inter-class discriminative power of the deep features and their intra-class compactness. In particular, one loss function promotes the aggregation of the feature points around the centres of the view they belong to, within the scope of their own identity. The second loss encourages to push away from each other the feature clusters corresponding simultaneously to different views and different identities. Under the supervision of the two new objectives we achieve state-of-the-art accuracy with ResNet50 on Market-1501 and CUHK03 datasets, beating the performance of the softmax loss.
Original languageEnglish
Title of host publicationIrish Machine Vision and Image Processing Conference 2017: Proceedings
PublisherIrish Pattern Recognition & Classification Society
ISBN (Print)ISBN 978-0-9934207-2-6
Publication statusEarly online date - 01 Jul 2017
EventIrish Machine Vision and Image Processing Conference 2017 - Maynooth University, Maynooth, Ireland
Duration: 30 Aug 201701 Sep 2017
http://imvip2017.cs.nuim.ie/

Conference

ConferenceIrish Machine Vision and Image Processing Conference 2017
Abbreviated titleIMVIP 2017
CountryIreland
CityMaynooth
Period30/08/201701/09/2017
Internet address

Fingerprint Dive into the research topics of 'A Tale of Two Losses: Discriminative Deep Feature Learning for Person Re-Identification'. Together they form a unique fingerprint.

Cite this