Revisiting Reweighted Risk for Calibration: AURC, Focal, and Inverse Focal Loss
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910003902808064 |
|---|---|
| author | Zhou, Han Gruber, Sebastian G. Popordanoska, Teodora Blaschko, Matthew B. |
| author_facet | Zhou, Han Gruber, Sebastian G. Popordanoska, Teodora Blaschko, Matthew B. |
| contents | Several variants of reweighted risk functionals, such as focal loss, inverse focal loss, and the Area Under the Risk Coverage Curve (AURC), have been proposed for improving model calibration; yet their theoretical connections to calibration errors remain under-explored. In this paper, we revisit a broad class of weighted risk functions and find a principled connection between calibration error and selective classification. We show that minimizing calibration error is closely linked to the selective classification paradigm and demonstrate that optimizing selective risk in low confidence regions naturally improves calibration. Our proposed loss shares a similar reweighting strategy with dual focal loss but offers greater flexibility through the choice of confidence score functions (CSFs). Furthermore, our approach utilizes a bin-based cumulative distribution function (CDF) approximation, enabling efficient gradient-based optimization with O(nM) complexity for n samples and M bins. Empirical evaluations demonstrate that our method achieves competitive calibration performance across a range of datasets and model architectures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_23463 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Revisiting Reweighted Risk for Calibration: AURC, Focal, and Inverse Focal Loss Zhou, Han Gruber, Sebastian G. Popordanoska, Teodora Blaschko, Matthew B. Computer Vision and Pattern Recognition Several variants of reweighted risk functionals, such as focal loss, inverse focal loss, and the Area Under the Risk Coverage Curve (AURC), have been proposed for improving model calibration; yet their theoretical connections to calibration errors remain under-explored. In this paper, we revisit a broad class of weighted risk functions and find a principled connection between calibration error and selective classification. We show that minimizing calibration error is closely linked to the selective classification paradigm and demonstrate that optimizing selective risk in low confidence regions naturally improves calibration. Our proposed loss shares a similar reweighting strategy with dual focal loss but offers greater flexibility through the choice of confidence score functions (CSFs). Furthermore, our approach utilizes a bin-based cumulative distribution function (CDF) approximation, enabling efficient gradient-based optimization with O(nM) complexity for n samples and M bins. Empirical evaluations demonstrate that our method achieves competitive calibration performance across a range of datasets and model architectures. |
| title | Revisiting Reweighted Risk for Calibration: AURC, Focal, and Inverse Focal Loss |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.23463 |