Multi-Resolution Overlapping Stripes Network for Person Re-Identification

TL;DR

This paper introduces a multi-resolution overlapping stripes network that combines global and local features at various resolutions for improved person re-identification, addressing spatial variation and part correlation issues.

Contribution

It proposes a novel multi-resolution, part-based network with overlapping stripes and multiple loss functions, enhancing feature representation for person re-identification.

Findings

Outperforms state-of-the-art methods on benchmark datasets.

Effectively combines local and global features for better accuracy.

Addresses spatial variation and part correlation in re-identification.

Abstract

This paper addresses the person re-identification (PReID) problem by combining global and local information at multiple feature resolutions with different loss functions. Many previous studies address this problem using either part-based features or global features. In case of part-based representation, the spatial correlation between these parts is not considered, while global-based representation are not sensitive to spatial variations. This paper presents a part-based model with a multi-resolution network that uses different level of features. The output of the last two conv blocks is then partitioned horizontally and processed in pairs with overlapping stripes to cover the important information that might lie between parts. We use different loss functions to combine local and global information for classification. Experimental results on a benchmark dataset demonstrate that the presented method outperforms the state-of-the-art methods.