Horizontal Pyramid Matching for Person Re-identification

TL;DR

This paper introduces Horizontal Pyramid Matching (HPM), a novel approach for person re-identification that leverages multi-scale partial features and pooling strategies to improve robustness against missing body parts, achieving state-of-the-art results.

Contribution

The paper proposes a simple yet effective HPM method that enhances feature robustness by classifying partial features at multiple scales and using pooling strategies, advancing Re-ID accuracy.

Findings

Achieved new state-of-the-art mAP scores on Market-1501, DukeMTMC-ReID, and CUHK03 datasets.

Demonstrated robustness of HPM against missing body parts in person images.

Validated effectiveness through extensive experiments on popular benchmarks.

Abstract

Despite the remarkable recent progress, person re-identification (Re-ID) approaches are still suffering from the failure cases where the discriminative body parts are missing. To mitigate such cases, we propose a simple yet effective Horizontal Pyramid Matching (HPM) approach to fully exploit various partial information of a given person, so that correct person candidates can be still identified even even some key parts are missing. Within the HPM, we make the following contributions to produce a more robust feature representation for the Re-ID task: 1) we learn to classify using partial feature representations at different horizontal pyramid scales, which successfully enhance the discriminative capabilities of various person parts; 2) we exploit average and max pooling strategies to account for person-specific discriminative information in a global-local manner. To validate the effectiveness of the proposed HPM, extensive experiments are conducted on three popular benchmarks, including Market-1501, DukeMTMC-ReID and CUHK03. In particular, we achieve mAP scores of 83.1%, 74.5% and 59.7% on these benchmarks, which are the new state-of-the-arts. Our code is available on Github