Dual-level Fuzzy Learning with Patch Guidance for Image Ordinal Regression

TL;DR

This paper introduces DFPG, a novel framework for image ordinal regression that uses patch guidance and fuzzy logic to improve classification accuracy by leveraging patch-level features from only image-level labels.

Contribution

The paper proposes a dual-level fuzzy learning framework with patch guidance that effectively captures label ambiguity and focuses on patch-level features using only image-level ordinal labels.

Findings

Outperforms existing methods on various datasets

Effectively distinguishes difficult-to-classify categories

Demonstrates superior handling of label ambiguity

Abstract

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.