MedXplore: Towards Reliable and Unbiased Generalized Category Discovery in Medical Imaging

arXiv:2607.27620v1 Announce Type: new Abstract: Deep learning has shown strong potential in medical image analysis, but most existing methods rely on large-scale annotations and a closed-world assumption that rarely holds in clinical practice. Although Generalized Category Discovery (GCD) has advanced rapidly on natural images, it remains underexplored in medical imaging. To address this issue, we propose MedXplore, a unified framework for reliable and unbiased medical GCD, optimizing from both perceptual and decision levels. Specifically, at the perceptual level, taking a frequency domain perspective, Frequency-SNR Adaptive Attention and Consistency (FAAC) performs learnable full-spectrum filtering and global-local energy contrast activation to not only highlight local abnormal signals relative to the global context, but also provide reliable semantic anchors for patch consistency learning. At the decision level, Adaptive Cosine-Angular Margin (ACAM) adjusts angular margins using semantic difficulty and feature confidence to balance intra-class compactness and inter-class separability. Together, the two modules improve lesion-sensitive representation learning and mitigate old-class bias. Experiments on multiple benchmarks show an average extbf{8.5%} gain in extit{All} accuracy over the strongest competing methods. On Kvasir, MedXplore reduces false-old errors from 14.50% to 0.80%, demonstrating strong robustness under severe old-new ambiguity.

Related

• Generalized Category Discovery in Federated Graph Learning
• Case-Aware Medical Image Classification with Multimodal Knowledge Graphs and Reliability-Guided Refinement
• Adaptive Conformal Prediction for Reliable and Explainable Medical Image Classification

Source: arXiv cs.CV | 2026-07-31