Pose-Guided Feature Learning with Knowledge Distillation for Occluded Person Re-Identification

07/31/2021
by   Kecheng Zheng, et al.
8

Occluded person re-identification (ReID) aims to match person images with occlusion. It is fundamentally challenging because of the serious occlusion which aggravates the misalignment problem between images. At the cost of incorporating a pose estimator, many works introduce pose information to alleviate the misalignment in both training and testing. To achieve high accuracy while preserving low inference complexity, we propose a network named Pose-Guided Feature Learning with Knowledge Distillation (PGFL-KD), where the pose information is exploited to regularize the learning of semantics aligned features but is discarded in testing. PGFL-KD consists of a main branch (MB), and two pose-guided branches, , a foreground-enhanced branch (FEB), and a body part semantics aligned branch (SAB). The FEB intends to emphasise the features of visible body parts while excluding the interference of obstructions and background (, foreground feature alignment). The SAB encourages different channel groups to focus on different body parts to have body part semantics aligned representation. To get rid of the dependency on pose information when testing, we regularize the MB to learn the merits of the FEB and SAB through knowledge distillation and interaction-based training. Extensive experiments on occluded, partial, and holistic ReID tasks show the effectiveness of our proposed network.

READ FULL TEXT

page 2

page 3

page 4

page 5

page 6

page 7

page 8

page 9

research
12/05/2021

Pose-guided Feature Disentangling for Occluded Person Re-identification Based on Transformer

Occluded person re-identification is a challenging task as human body pa...
research
11/29/2021

PGGANet: Pose Guided Graph Attention Network for Person Re-identification

Person re-identification (ReID) aims at retrieving a person from images ...
research
05/16/2021

Neighbourhood-guided Feature Reconstruction for Occluded Person Re-Identification

Person images captured by surveillance cameras are often occluded by var...
research
11/07/2022

Body Part-Based Representation Learning for Occluded Person Re-Identification

Occluded person re-identification (ReID) is a person retrieval task whic...
research
05/30/2019

Semantics-Aligned Representation Learning for Person Re-identification

Person re-identification (reID) aims to match person images to retrieve ...
research
03/18/2020

High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification

Occluded person re-identification (ReID) aims to match occluded person i...
research
04/10/2019

Foreground-aware Pyramid Reconstruction for Alignment-free Occluded Person Re-identification

Re-identifying a person across multiple disjoint camera views is importa...

Please sign up or login with your details

Forgot password? Click here to reset