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.
@article{arxiv.2004.06271,
title = {The Devil is in the Details: Self-Supervised Attention for Vehicle Re-Identification},
author = {Pirazh Khorramshahi and Neehar Peri and Jun-cheng Chen and Rama Chellappa},
journal= {arXiv preprint arXiv:2004.06271},
year = {2020}
}
Comments
This work has been accepted European Conference on Computer Vision (ECCV) 2020