CVAug 31, 2020

Receptive Multi-granularity Representation for Person Re-Identification

arXiv:2008.13450v13 citations
Originality Incremental advance
AI Analysis

This work addresses misalignment and part inconsistency in person re-identification, an incremental improvement for computer vision applications like surveillance.

The paper tackles the problem of inconsistent local details in person re-identification by proposing a receptive multi-granularity learning approach, achieving state-of-the-art accuracy of 96.2% Rank-1 and 90.0% mAP on the Market-1501 benchmark.

A key for person re-identification is achieving consistent local details for discriminative representation across variable environments. Current stripe-based feature learning approaches have delivered impressive accuracy, but do not make a proper trade-off between diversity, locality, and robustness, which easily suffers from part semantic inconsistency for the conflict between rigid partition and misalignment. This paper proposes a receptive multi-granularity learning approach to facilitate stripe-based feature learning. This approach performs local partition on the intermediate representations to operate receptive region ranges, rather than current approaches on input images or output features, thus can enhance the representation of locality while remaining proper local association. Toward this end, the local partitions are adaptively pooled by using significance-balanced activations for uniform stripes. Random shifting augmentation is further introduced for a higher variance of person appearing regions within bounding boxes to ease misalignment. By two-branch network architecture, different scales of discriminative identity representation can be learned. In this way, our model can provide a more comprehensive and efficient feature representation without larger model storage costs. Extensive experiments on intra-dataset and cross-dataset evaluations demonstrate the effectiveness of the proposed approach. Especially, our approach achieves a state-of-the-art accuracy of 96.2%@Rank-1 or 90.0%@mAP on the challenging Market-1501 benchmark.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes