Dual-level Fuzzy Learning with Patch Guidance for Image Ordinal Regression
This work addresses the challenge of fine-grained feature learning in image ordinal regression for applications like medical grading, but it is incremental as it builds on existing methods by incorporating patch-level guidance and fuzzy logic.
The paper tackles the problem of image ordinal regression by addressing the limitation of using only image-level ordinal labels, which overlooks patch-level features, and proposes a Dual-level Fuzzy Learning with Patch Guidance framework that learns precise grading boundaries from ambiguous labels with patch-level supervision, achieving superior performance on various datasets.
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.