Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2403.00561 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917601658011648 |
|---|---|
| author | Yuan, Huaqing He, Yi Du, Peng Song, Lu |
| author_facet | Yuan, Huaqing He, Yi Du, Peng Song, Lu |
| contents | Face images contain a wide variety of attribute information. In this paper, we propose a generalized framework for joint estimation of ordinal and nominal attributes based on information sharing. We tackle the correlation problem between heterogeneous attributes using hard parameter sharing of shallow features, and trade-off multiple loss functions by considering homoskedastic uncertainty for each attribute estimation task. This leads to optimal estimation of multiple attributes of the face and reduces the training cost of multitask learning. Experimental results on benchmarks with multiple face attributes show that the proposed approach has superior performance compared to state of the art. Finally, we discuss the bias issues arising from the proposed approach in face attribute estimation and validate its feasibility on edge systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_00561 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Multi-Task Learning Using Uncertainty to Weigh Losses for Heterogeneous Face Attribute Estimation Yuan, Huaqing He, Yi Du, Peng Song, Lu Computer Vision and Pattern Recognition Artificial Intelligence Face images contain a wide variety of attribute information. In this paper, we propose a generalized framework for joint estimation of ordinal and nominal attributes based on information sharing. We tackle the correlation problem between heterogeneous attributes using hard parameter sharing of shallow features, and trade-off multiple loss functions by considering homoskedastic uncertainty for each attribute estimation task. This leads to optimal estimation of multiple attributes of the face and reduces the training cost of multitask learning. Experimental results on benchmarks with multiple face attributes show that the proposed approach has superior performance compared to state of the art. Finally, we discuss the bias issues arising from the proposed approach in face attribute estimation and validate its feasibility on edge systems. |
| title | Multi-Task Learning Using Uncertainty to Weigh Losses for Heterogeneous Face Attribute Estimation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2403.00561 |