Robust Person Re-Identification through Contextual Mutual Boosting

09/16/2020
by   Zhikang Wang, et al.
0

Person Re-Identification (Re-ID) has witnessed great advance, driven by the development of deep learning. However, modern person Re-ID is still challenged by background clutter, occlusion and large posture variation which are common in practice. Previous methods tackle these challenges by localizing pedestrians through external cues (e.g., pose estimation, human parsing) or attention mechanism, suffering from high computation cost and increased model complexity. In this paper, we propose the Contextual Mutual Boosting Network (CMBN). It localizes pedestrians and recalibrates features by effectively exploiting contextual information and statistical inference. Firstly, we construct two branches with a shared convolutional frontend to learn the foreground and background features respectively. By enabling interaction between these two branches, they boost the accuracy of the spatial localization mutually. Secondly, starting from a statistical perspective, we propose the Mask Generator that exploits the activation distribution of the transformation matrix for generating the static channel mask to the representations. The mask recalibrates the features to amplify the valuable characteristics and diminish the noise. Finally, we propose the Contextual-Detachment Strategy to optimize the two branches jointly and independently, which further enhances the localization precision. Experiments on the benchmarks demonstrate the superiority of the architecture compared the state-of-the-art.

READ FULL TEXT

page 4

page 5

research
11/21/2018

Adaptive Re-ranking of Deep Feature for Person Re-identification

Typical person re-identification (re-ID) methods train a deep CNN to ext...
research
03/20/2023

Attention Disturbance and Dual-Path Constraint Network for Occluded Person Re-Identification

Occluded person re-identification (Re-ID) aims to address the potential ...
research
11/29/2021

Learning Context-Aware Embedding for Person Search

Person Search is a relevant task that aims to jointly solve Person Detec...
research
10/25/2019

An End-to-End Foreground-Aware Network for Person Re-Identification

Person re-identification is a crucial task of identifying pedestrians of...
research
07/14/2023

Erasing, Transforming, and Noising Defense Network for Occluded Person Re-Identification

Occlusion perturbation presents a significant challenge in person re-ide...
research
07/25/2021

Spatio-Temporal Representation Factorization for Video-based Person Re-Identification

Despite much recent progress in video-based person re-identification (re...

Please sign up or login with your details

Forgot password? Click here to reset