Exploring Fine-Grained Representation and Recomposition for Cloth-Changing Person Re-Identification

TL;DR

This paper introduces FIRe$^{2}$, a novel framework for cloth-changing person re-identification that learns discriminative features without auxiliary data by clustering images based on fine-grained attributes and recomposing features to improve robustness.

Contribution

The paper proposes a new framework combining fine-grained feature mining and attribute recomposition, enabling cloth-changing person Re-ID without auxiliary annotations or data.

Findings

Achieves state-of-the-art results on five cloth-changing Re-ID benchmarks.

Effective clustering of images based on fine-grained attributes.

Recomposition of features enhances robustness and discriminability.

Abstract

Cloth-changing person Re-IDentification (Re-ID) is a particularly challenging task, suffering from two limitations of inferior discriminative features and limited training samples. Existing methods mainly leverage auxiliary information to facilitate identity-relevant feature learning, including soft-biometrics features of shapes or gaits, and additional labels of clothing. However, this information may be unavailable in real-world applications. In this paper, we propose a novel FIne-grained Representation and Recomposition (FIRe$^{2}$) framework to tackle both limitations without any auxiliary annotation or data. Specifically, we first design a Fine-grained Feature Mining (FFM) module to separately cluster images of each person. Images with similar so-called fine-grained attributes (e.g., clothes and viewpoints) are encouraged to cluster together. An attribute-aware classification loss is introduced to perform fine-grained learning based on cluster labels, which are not shared among different people, promoting the model to learn identity-relevant features. Furthermore, to take full advantage of fine-grained attributes, we present a Fine-grained Attribute Recomposition (FAR) module by recomposing image features with different attributes in the latent space. It significantly enhances robust feature learning. Extensive experiments demonstrate that FIRe$^{2}$ can achieve state-of-the-art performance on five widely-used cloth-changing person Re-ID benchmarks. The code is available at https://github.com/QizaoWang/FIRe-CCReID.