Learning Resolution-Adaptive Representations for Cross-Resolution Person Re-Identification

TL;DR

This paper introduces a novel resolution-adaptive representation learning approach for cross-resolution person re-identification, eliminating the need for super-resolution modules and achieving state-of-the-art results.

Contribution

It proposes two resolution-adaptive mechanisms—disentangling resolution-specific info and learning adaptive masks—along with a progressive training strategy, advancing CRReID performance.

Findings

Outperforms existing methods on multiple benchmarks

Achieves state-of-the-art accuracy in CRReID tasks

Effectively handles resolution variations without super-resolution modules

Abstract

The cross-resolution person re-identification (CRReID) problem aims to match low-resolution (LR) query identity images against high resolution (HR) gallery images. It is a challenging and practical problem since the query images often suffer from resolution degradation due to the different capturing conditions from real-world cameras. To address this problem, state-of-the-art (SOTA) solutions either learn the resolution-invariant representation or adopt super-resolution (SR) module to recover the missing information from the LR query. This paper explores an alternative SR-free paradigm to directly compare HR and LR images via a dynamic metric, which is adaptive to the resolution of a query image. We realize this idea by learning resolution-adaptive representations for cross-resolution comparison. Specifically, we propose two resolution-adaptive mechanisms. The first one disentangles the resolution-specific information into different sub-vectors in the penultimate layer of the deep neural networks, and thus creates a varying-length representation. To better extract resolution-dependent information, we further propose to learn resolution-adaptive masks for intermediate residual feature blocks. A novel progressive learning strategy is proposed to train those masks properly. These two mechanisms are combined to boost the performance of CRReID. Experimental results show that the proposed method is superior to existing approaches and achieves SOTA performance on multiple CRReID benchmarks.