MIFR: A Modality-Invariant and Fair Representation Framework for Skin Disease Classification

arXiv:2608.18774v1 Announce Type: new Abstract: Skin diseases represent a major global public health burden, yet machine learning tools developed to assist in their diagnosis suffer from two critical limitations: reliance on only one modality for diagnosis and systematic performance disparities across skin tones. While existing approaches address each challenge separately, this work proposes a modality-invariant framework with fair representation (MIFR) for skin disease classification. The architecture pairs clinical photographs with dermoscopic images using ViT-based encoders, projecting each input into a high-dimensional embedding space via modality-specific projection heads. The resulting model is trained with a five-component multi-objective loss including weighted cross-entropy for classification, confusion and skin-type classification losses for fairness, per-modality supervised contrastive loss for class alignment, and a modality-invariance loss for clinical and dermoscopic modality alignment. Experiments on the HIBA+Derm7pt paired dataset and the external PAD-UFES-20 and ISIC 2019 datasets showed that modality-invariant representation learning provides competitive predictive performance compare to relevant baseline models and competitive fairness on the internal dataset. t-SNE visualizations confirmed that clinical and dermoscopic embeddings of the same disease are geometrically aligned, validating the joint objectives.

Related

• UniMod: Enhancing Multi-Modal Medical Diagnosis through Cross-Modality and Within-Modality Alignment
• IViT: A Novel Interpretable Visual Transformer for Skin Disease Detection
• A Picture Says Thousands of Words - Harnessing Dermal Exposure Data from Images through Hybrid Deep Learning for Enhanced Safety Assessment

Source: arXiv cs.CV | 2026-08-20