Dual-level Fuzzy Learning with Patch Guidance for Image Ordinal Regression
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912380692201472 |
|---|---|
| author | Dong, Chunlai Ying, Haochao Qiu, Qibo Wang, Jinhong Chen, Danny Wu, Jian |
| author_facet | Dong, Chunlai Ying, Haochao Qiu, Qibo Wang, Jinhong Chen, Danny Wu, Jian |
| contents | Ordinal regression bridges regression and classification by assigning objects to ordered classes. While human experts rely on discriminative patch-level features for decisions, current approaches are limited by the availability of only image-level ordinal labels, overlooking fine-grained patch-level characteristics. In this paper, we propose a Dual-level Fuzzy Learning with Patch Guidance framework, named DFPG that learns precise feature-based grading boundaries from ambiguous ordinal labels, with patch-level supervision. Specifically, we propose patch-labeling and filtering strategies to enable the model to focus on patch-level features exclusively with only image-level ordinal labels available. We further design a dual-level fuzzy learning module, which leverages fuzzy logic to quantitatively capture and handle label ambiguity from both patch-wise and channel-wise perspectives. Extensive experiments on various image ordinal regression datasets demonstrate the superiority of our proposed method, further confirming its ability in distinguishing samples from difficult-to-classify categories. The code is available at https://github.com/ZJUMAI/DFPG-ord. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_05834 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Dual-level Fuzzy Learning with Patch Guidance for Image Ordinal Regression Dong, Chunlai Ying, Haochao Qiu, Qibo Wang, Jinhong Chen, Danny Wu, Jian Computer Vision and Pattern Recognition Ordinal regression bridges regression and classification by assigning objects to ordered classes. While human experts rely on discriminative patch-level features for decisions, current approaches are limited by the availability of only image-level ordinal labels, overlooking fine-grained patch-level characteristics. In this paper, we propose a Dual-level Fuzzy Learning with Patch Guidance framework, named DFPG that learns precise feature-based grading boundaries from ambiguous ordinal labels, with patch-level supervision. Specifically, we propose patch-labeling and filtering strategies to enable the model to focus on patch-level features exclusively with only image-level ordinal labels available. We further design a dual-level fuzzy learning module, which leverages fuzzy logic to quantitatively capture and handle label ambiguity from both patch-wise and channel-wise perspectives. Extensive experiments on various image ordinal regression datasets demonstrate the superiority of our proposed method, further confirming its ability in distinguishing samples from difficult-to-classify categories. The code is available at https://github.com/ZJUMAI/DFPG-ord. |
| title | Dual-level Fuzzy Learning with Patch Guidance for Image Ordinal Regression |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.05834 |