cs.CVFeb 23, 2026

Contrastive meta-domain adaptation for robust skin lesion classification across clinical and acquisition conditions

Authors: Rodrigo Mota, Kelvin Cunha, Emanoel dos Santos, Fábio Papais, Francisco Filho, Thales Bezerra, Erico Medeiros, Paulo Borba, +1 more

Organizations: Centro de Informática, Universidade Federal de Pernambuco, Brazil

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Deep learning models for dermatological image analysis remain sensitive to acquisition variability and domain-specific visual characteristics, leading to performance degradation when deployed in clinical settings. We investigate how visual artifacts and domain shifts affect deep learning-based skin lesion classification. We propose an adaptation strategy, grounded in the idea of visual meta-domains, that transfers visual representations from larger dermoscopic datasets into clinical image domains, thereby improving generalization robustness. Experiments across multiple dermatology datasets show consistent gains in classification performance and reduced gaps between dermoscopic and clinical images. These results emphasize the importance of domain-aware training for deployable systems.

Figures & tables

Figure 1: Overview of the domain adaptation strategy. Instead of directly transferring features from a previously trained dataset (left), we introduce meta-domain adaptation that aligns the visual representations of the source domain with those of the target domain (right).
Figure 2: Color-based appearance transformations applied to the source domain to generate KK meta-domains, derived from randomly selected calibration subsets for domain adaptation.
Figure 3: Contrastive pre-training on HAM10000 test set. Naive training is compared with contrastive optimization to mitigate robustness degradation in visual domain features.
 PAD-UFES-20 [ 5 ]DDI [ 4 ]
 ACCF1PrecisionRecallACCF1PrecisionRecall
Pacheco et. al. [ 5 ] (only image)0.690.70.730.69----
Daneshjou et al. [ 4 ]----0.770.760.760.77
Naive (backprop)0.350.380.380.390.120.050.040.11
Naive + Fine-tuning (FT)0.710.640.60.690.50.530.540.53
Naive + CT-pretrain0.760.720.710.730.490.30.280.33
Table 1: Comparison of naive training, traditional fine-tuning with augmentation, and the proposed contrastive pre-training (CT-pretrain) and guided-tuning (GT) strategies. We replicate the baseline methods reported in [ 5 , 4 ] and evaluate all approaches on their respective datasets. Metrics include accuracy, precision, recall, and F1-score.
Figure 4: Validation of guided-tuning on PAD increasing the training set size.
Figure 5: Comparison between the guided-tuning and naive training. Naive backpropagation adapts to the current domain but exhibits forgetting of previously learned domains and poor generalization to unseen ones.

Explore similar work

CardsList

  1. Bridging Research and Practice: A Systematic Evaluation of Generalist and Dermatology-Specific Models in Clinical Skin Lesion Classification

    Oct 2, 2026Emanoel dos Santos, Kelvin Cunha, Rodrigo Mota +8Skin Lesion ClassificationCross-Dataset Generalization

    Centro de Informática, Universidade Federal de Pernambuco (UFPE), Brazil · Hospital das Clinicas, Ebserh, UFPE, Pernambuco, Brazil

  2. Searching for Robust Augmentations to Improve Out-of-Domain Generalization in Dermoscopic Skin Cancer Classification

    Jul 29, 2026Alexander Kozachok, Ilya Latyshev, Evgeny Karpulevich +3Skin Lesion ClassificationData Augmentation

    Trusted AI Research Center, Russian Academy of Sciences, 109004 Moscow, Russia

  3. CoFiDA-M: Concept-Aware Feature Modulation for Cross-Domain Adaptation with Image-Only Inference

    May 29, 2026Nurjahan Sultana, Moi Hoon Yap, Xinqi Fan +1Skin Lesion ClassificationMedical Image Classification

    Department of Computing and Mathematics, Manchester Metropolitan University Dalton Building, Chester Street, M1 5GD Manchester, UK