Gait Recognition with Mask-based Regularization
- Publisher:
- IEEE
- Publication Type:
- Conference Proceeding
- Citation:
- 2023 IEEE International Joint Conference on Biometrics (IJCB), 2024, 00, pp. 1-10
- Issue Date:
- 2024-03-01
Closed Access
| Filename | Description | Size | |||
|---|---|---|---|---|---|
| 1716007.pdf | Published version | 758.75 kB |
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
Most gait recognition methods exploit spatial temporal representations from static appearances and dynamic walking patterns However we observe that many part based methods neglect representations at boundaries In addition the phenomenon of overfitting on training data is relatively common in gait recognition which is perhaps due to insufficient data and low informative gait silhouettes Motivated by these observations we propose a novel mask based regularization method named ReverseMask By injecting perturbation on the feature map the proposed regularization method helps convolutional architecture learn the discriminative representations and enhances generalization Also we design an Inception like ReverseMask Block which has three branches composed of a global branch a feature dropping branch and a feature scaling branch Precisely the dropping branch can extract fine grained representations when partial activations are zero outed Meanwhile the scaling branch randomly scales the feature map keeping structural information of activations and preventing overfitting The plug and play Inception like ReverseMask block is simple and effective improving the performance of many state of the art methods Extensive experiments demonstrate that the ReverseMask regularization help baseline achieves higher accuracy and better generalization Moreover the base line with Inception like Block significantly outperforms state of the art methods on the two most popular datasets CASIA B and OUMVLP
Please use this identifier to cite or link to this item: