The Devil is in the Details: Self-Supervised Attention for Vehicle Re-Identification release_z3cn4maofbhshg35s2i3cz42o4

by Pirazh Khorramshahi, Neehar Peri, Jun-cheng Chen, Rama Chellappa

Released as a article .

2020  

Abstract

In recent years, the research community has approached the problem of vehicle re-identification (re-id) with attention-based models, specifically focusing on regions of a vehicle containing discriminative information. These re-id methods rely on expensive key-point labels, part annotations, and additional attributes including vehicle make, model, and color. Given the large number of vehicle re-id datasets with various levels of annotations, strongly-supervised methods are unable to scale across different domains. In this paper, we present Self-supervised Attention for Vehicle Re-identification (SAVER), a novel approach to effectively learn vehicle-specific discriminative features. Through extensive experimentation, we show that SAVER improves upon the state-of-the-art on challenging VeRi, VehicleID, Vehicle-1M and VERI-Wild datasets.
In text/plain format

Archived Files and Locations

application/pdf  5.6 MB
file_vtkjsx5l7jelnd7hgyhxaopfvq
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2020-07-17
Version   v3
Language   en ?
arXiv  2004.06271v3
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: ff39908f-0403-4b5c-8513-b53b5dea5d4d
API URL: JSON