Low Resolution Information Also Matters: Learning Multi-Resolution Representations for Person Re-Identification

TL;DR

This paper introduces a novel multi-resolution learning approach for person re-identification that leverages both low and high resolution features, outperforming existing super-resolution based methods.

Contribution

The paper proposes MRJL, a method combining resolution reconstruction and dual feature fusion to utilize information from multiple resolutions in person re-ID.

Findings

Outperforms state-of-the-art methods on five benchmarks.

Effectively leverages low-resolution information for better re-ID accuracy.

Demonstrates the importance of multi-resolution features in cross-resolution scenarios.

Abstract

As a prevailing task in video surveillance and forensics field, person re-identification (re-ID) aims to match person images captured from non-overlapped cameras. In unconstrained scenarios, person images often suffer from the resolution mismatch problem, i.e., \emph{Cross-Resolution Person Re-ID}. To overcome this problem, most existing methods restore low resolution (LR) images to high resolution (HR) by super-resolution (SR). However, they only focus on the HR feature extraction and ignore the valid information from original LR images. In this work, we explore the influence of resolutions on feature extraction and develop a novel method for cross-resolution person re-ID called \emph{\textbf{M}ulti-Resolution \textbf{R}epresentations \textbf{J}oint \textbf{L}earning} (\textbf{MRJL}). Our method consists of a Resolution Reconstruction Network (RRN) and a Dual Feature Fusion Network (DFFN). The RRN uses an input image to construct a HR version and a LR version with an encoder and two decoders, while the DFFN adopts a dual-branch structure to generate person representations from multi-resolution images. Comprehensive experiments on five benchmarks verify the superiority of the proposed MRJL over the relevent state-of-the-art methods.