Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

1-2023

Abstract

Object appearances change dramatically with pose variations. This creates a challenge for embedding schemes that seek to map instances with the same object ID to locations that are as close as possible. This issue becomes significantly heightened in complex computer vision tasks such as re-identification(reID). In this paper, we suggest that these dramatic appearance changes are indications that an object ID is composed of multiple natural groups, and it is counterproductive to forcefully map instances from different groups to a common location. This leads us to introduce Relation Preserving Triplet Mining (RPTM), a feature matching guided triplet mining scheme, that ensures that triplets will respect the natural subgroupings within an object ID. We use this triplet mining mechanism to establish a pose-aware, well-conditioned triplet loss by implicitly enforcing view consistency. This allows a single network to be trained with fixed parameters across datasets, while providing state-of-the-art results. Code is available at https://github.com/adhirajghosh/RPTM_reid.

Keywords

Algorithms, Machine learning architectures, and algorithms (including transfer), formulations, Image recognition and understanding (object detection, categorization, segmentation, scene modeling, visual reasoning)

Discipline

Databases and Information Systems | Graphics and Human Computer Interfaces

Research Areas

Data Science and Engineering

Publication

2023 23rd IEEE/CVF Winter Conference on Applications of Computer Vision WACV: Virtual, January 3-7: Proceedings

First Page

4829

Last Page

4838

ISBN

9781665493468

Identifier

10.1109/WACV56688.2023.00482

Publisher

IEEE

City or Country

Piscataway, NJ

Additional URL

https://doi.org/10.1109/WACV56688.2023.00482

Share

COinS