The Devil Is in the Details: Self-Supervised Attention for Vehicle Re-Identification
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.
Cite
Text
Khorramshahi et al. "The Devil Is in the Details: Self-Supervised Attention for Vehicle Re-Identification." Proceedings of the European Conference on Computer Vision (ECCV), 2020. doi:10.1007/978-3-030-58568-6_22Markdown
[Khorramshahi et al. "The Devil Is in the Details: Self-Supervised Attention for Vehicle Re-Identification." Proceedings of the European Conference on Computer Vision (ECCV), 2020.](https://mlanthology.org/eccv/2020/khorramshahi2020eccv-devil/) doi:10.1007/978-3-030-58568-6_22BibTeX
@inproceedings{khorramshahi2020eccv-devil,
title = {{The Devil Is in the Details: Self-Supervised Attention for Vehicle Re-Identification}},
author = {Khorramshahi, Pirazh and Peri, Neehar and Chen, Jun-cheng and Chellappa, Rama},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2020},
doi = {10.1007/978-3-030-58568-6_22},
url = {https://mlanthology.org/eccv/2020/khorramshahi2020eccv-devil/}
}