Deeply-Learned Part-Aligned Representations for Person Re-Identification

TL;DR

This paper introduces a deep learning method for person re-identification that uses part-aligned representations to improve robustness against pose variations and spatial misalignments, achieving state-of-the-art results.

Contribution

The paper proposes a novel deep neural network that learns human body part alignment without labels, enhancing person re-identification accuracy over existing methods.

Findings

Achieves state-of-the-art performance on multiple datasets.

Robust to pose changes and spatial distribution variations.

Does not require body part labeling for training.

Abstract

In this paper, we address the problem of person re-identification, which refers to associating the persons captured from different cameras. We propose a simple yet effective human part-aligned representation for handling the body part misalignment problem. Our approach decomposes the human body into regions (parts) which are discriminative for person matching, accordingly computes the representations over the regions, and aggregates the similarities computed between the corresponding regions of a pair of probe and gallery images as the overall matching score. Our formulation, inspired by attention models, is a deep neural network modeling the three steps together, which is learnt through minimizing the triplet loss function without requiring body part labeling information. Unlike most existing deep learning algorithms that learn a global or spatial partition-based local representation, our approach performs human body partition, and thus is more robust to pose changes and various human spatial distributions in the person bounding box. Our approach shows state-of-the-art results over standard datasets, Market-$1501$, CUHK$03$, CUHK$01$ and VIPeR.