Multi-shot Person Re-identification through Set Distance with Visual Distributional Representation

TL;DR

This paper introduces a novel visual distributional representation for multi-shot person re-identification, modeling image sets as distributions and using Wasserstein distance for improved set comparison, outperforming existing methods.

Contribution

It proposes a new distributional approach with Wasserstein distance for multi-shot person re-id, capturing matching evidence more effectively than pooling strategies.

Findings

Outperforms state-of-the-art methods on public datasets

Effectively models appearance variations with distributional representation

Natural alignment of image sets via Wasserstein distance

Abstract

Person re-identification aims to identify a specific person at distinct times and locations. It is challenging because of occlusion, illumination, and viewpoint change in camera views. Recently, multi-shot person re-id task receives more attention since it is closer to real-world application. A key point of a good algorithm for multi-shot person re-id is the temporal aggregation of the person appearance features. While most of the current approaches apply pooling strategies and obtain a fixed-size vector representation, these may lose the matching evidence between examples. In this work, we propose the idea of visual distributional representation, which interprets an image set as samples drawn from an unknown distribution in appearance feature space. Based on the supervision signals from a downstream task of interest, the method reshapes the appearance feature space and further learns the unknown distribution of each image set. In the context of multi-shot person re-id, we apply this novel concept along with Wasserstein distance and learn a distributional set distance function between two image sets. In this way, the proper alignment between two image sets can be discovered naturally in a non-parametric manner. Our experiment results on two public datasets show the advantages of our proposed method compared to other state-of-the-art approaches.