GaitSCM: Causal representation learning for gait recognition
Gait recognition is a promising biometric technology that aims to identify the target subject via walking pattern. Most existing appearance-based methods focus on learning discriminative spatio-temporal representations from gait silhouettes. However, these methods pay less attention to probing the c...
Saved in:
| Published in: | Computer vision and image understanding Vol. 243; p. 103995 |
|---|---|
| Main Authors: | , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Elsevier Inc
01.06.2024
|
| Subjects: | |
| ISSN: | 1077-3142, 1090-235X |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Gait recognition is a promising biometric technology that aims to identify the target subject via walking pattern. Most existing appearance-based methods focus on learning discriminative spatio-temporal representations from gait silhouettes. However, these methods pay less attention to probing the causality between identity factors and identity labels, which often mislead the model to learn gait representations that are susceptible to identity-irrelevant factors. In this paper, we attribute the cause that leads to the decline of model generalization under different external conditions to identity-irrelevant factors. We formulate the causalities among the identity factors, identity-irrelevant factors, and identity labels as a structural causal model (SCM). We accordingly propose a novel gait recognition framework named GaitSCM to learn covariate invariant gait representations, which is mainly composed of three components, including feature extraction module, feature disentanglement module, and backdoor adjustment. Specifically, we design a feature extractor with regard to the movement patterns of different body parts to learn fine-grained gait motion features, and then present a two-branch feature decoupling module to disentangle identity features and identity-irrelevant features with the aid of the classification confusion loss. To relieve the negative effect of identity-irrelevant factors, we develop a backdoor adjustment strategy to eliminate spurious associations between identity and identity-irrelevant features, which further facilitates the proposed framework to generate more powerful identity representations. Extensive experiments conducted on two public datasets validate the effectiveness of our method. The average Rank-1 can reach 93.2% and 90.4% on CASIA-B and OU-MVLP datasets, respectively, which verifies the superiority of GaitSCM. Source code is released at: https://github.com/HuoweiCode/GaitSCM.
•A novel causal representation learning framework GaitSCM for gait recognition is proposed.•A causal analysis based on SCM reveals the spurious relation in gait recognition.•Feature decoupling and backdoor adjustment are used to perform causal intervention.•GaitSCM achieves competitive results on the CASIA-B and OU-MVLP datasets. |
|---|---|
| ISSN: | 1077-3142 1090-235X |
| DOI: | 10.1016/j.cviu.2024.103995 |