Log In Sign Up

Resolution-invariant Person ReID Based on Feature Transformation and Self-weighted Attention

by   Ziyue Zhang, et al.

Person Re-identification (ReID) is a critical computer vision task which aims to match the same person in images or video sequences. Most current works focus on settings where the resolution of images is kept the same. However, the resolution is a crucial factor in person ReID, especially when the cameras are at different distances from the person or the camera's models are different from each other. In this paper, we propose a novel two-stream network with a lightweight resolution association ReID feature transformation (RAFT) module and a self-weighted attention (SWA) ReID module to evaluate features under different resolutions. RAFT transforms the low resolution features to corresponding high resolution features. SWA evaluates both features to get weight factors for the person ReID. Both modules are jointly trained to get a resolution-invariant representation. Extensive experiments on five benchmark datasets show the effectiveness of our method. For instance, we achieve Rank-1 accuracy of 43.3 state-of-the-art.


page 1

page 2

page 3

page 4


Resolution-invariant Person Re-Identification

Exploiting resolution invariant representation is critical for person Re...

Deep High-Resolution Representation Learning for Cross-Resolution Person Re-identification

Person re-identification (re-ID) tackles the problem of matching person ...

Resolution based Feature Distillation for Cross Resolution Person Re-Identification

Person re-identification (re-id) aims to retrieve images of same identit...

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

As a prevailing task in video surveillance and forensics field, person r...

Cross-Resolution Adversarial Dual Network for Person Re-Identification and Beyond

Person re-identification (re-ID) aims at matching images of the same per...

Self Attention Grid for Person Re-Identification

In this paper, we present an attention mechanism scheme to improve perso...

NFormer: Robust Person Re-identification with Neighbor Transformer

Person re-identification aims to retrieve persons in highly varying sett...