Person re-identification based on multi-scale feature learning

Extracting discriminative pedestrian features is an effective method in person re-identification. Most person re-identification works focus on extracting abstract features from the high-layer of the network, but ignore the middle-layer features, thus reducing the identity accuracy. To solve this problem, we construct a Smooth Aggregation Module (SAM) to extract, align, and fuse the feature maps in the middle-layer of the network to make up for the lack of detailed information in the high-level network features, and propose an Omni-Scale Feature Aggregation method (OSFA)(1) to jointly learn the abstract features and local detail features. Considering that the intra-class distance in person re-identification should be less than the inter-class distance, we combine multiple losses to constrain the model. We evaluate the performance of our method on three standard benchmark datasets: Market-1501, CUHK03 (both detected and labeled) and DukeMTMC-reID, and experimental results show that our method is superior to the state-of-the-art approaches. (C) 2021 Elsevier B.V. All rights reserved.

Automated summary

This study introduces a Smooth Aggregation Module (SAM) to extract, align, and fuse feature maps in the middle-layer of the network, and proposes an Omni-Scale Feature Aggregation method (OSFA) to jointly learn abstract features and local detail features, improving the identity accuracy in pedestrian re-identification.