HeadPose-Softmax: Head pose adaptive curriculum learning loss for deep face recognition
•Effective: HeadPose-Softmax significantly improves the accuracy of large pose face recognition while outperforming SOTA competitors on multiple face recognition benchmarks.•Easy: HeadPose-Softmax enables automatic adjustment of the importance of difficult samples during training without the need to...
Saved in:
| Published in: | Pattern recognition 2023-08, Vol.140, p.109552, Article 109552 |
|---|---|
| Main Authors: | , , , , , , |
| Format: | Article |
| Language: | eng |
| Subjects: | |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | •Effective: HeadPose-Softmax significantly improves the accuracy of large pose face recognition while outperforming SOTA competitors on multiple face recognition benchmarks.•Easy: HeadPose-Softmax enables automatic adjustment of the importance of difficult samples during training without the need to manually adjust the importance of each difficult sample.•Efficient: HeadPose-Softmax adds only negligible computational complexity to the training process and converges easily, and has the same cost as the backbone model in the inference process.
Face recognition has been one of the most popular applications in the field of target detection. Currently, frontal faces can be easily detected, but multi-view face detection remains a difficult task because of various factors such as illumination, various poses, occlusions, and facial expressions. Margin-based loss functions are used to increase the feature margins between different classes, thus enhancing the discriminability of face recognition models, but the performance in face detection in complex scenes (e.g., high pitch angle face detection in surveillance environments) can be significantly degraded. Recently, the idea of a mining-based strategy to emphasize hard samples has been used to achieve good results in multi-view face detection. However, most of the existing methods do not explicitly emphasize samples based on their importance, resulting in the underutilization of hard samples. In this paper, we propose a curriculum learning loss function (HeadPose-Softmax) to classify the difficulty of a sample based on its facial pose, and embed the concept of curriculum learning into the loss function to implement a novel training strategy for deep face recognition. The loss function explicitly emphasizes the importance of the samples according to the different difficulty of each sample, which allows the model to make fuller use of hard samples, focus on learning pose invariant features, and improve the accuracy of the model in multi-view face detection tasks. Specifically, our HeadPose-Softmax dynamically adjusts the relative importance of the hard samples according to the pose angle of the face in the hard samples during the training phase. At each stage, different samples are assigned different importance according to their corresponding difficulty. Extensive experimental results under popular benchmarks show that our HeadPose-Softmax can enhance the accuracy of the model in multi-view face detection and outperf |
|---|---|
| ISSN: | 0031-3203 1873-5142 |