SuperCon: Supervised Contrastive Learning for Imbalanced Skin Lesion Classification

Abstract

Convolutional neural networks (CNNs) have achieved great success in skin lesion classification. A balanced dataset is required to train a good model. However, due to the appearance of different skin lesions in practice, severe or even deadliest skin lesion types (e.g., melanoma) naturally have quite small amount represented in a dataset. In that, classification performance degradation occurs widely, it is significantly important to have CNNs that work well on class imbalanced skin lesion image dataset. In this paper, we propose SuperCon, a two-stage training strategy to overcome the class imbalance problem on skin lesion classification. It contains two stages: (i) representation training that tries to learn a feature representation that closely aligned among intra-classes and distantly apart from interclasses, and (ii) classifier fine-tuning that aims to learn a classifier that correctly predict the label based on the learnt representations. In the experimental evaluation, extensive comparisons have been made among our approach and other existing approaches on skin lesion benchmark datasets. The results show that our two-stage training strategy effectively addresses the class imbalance classification problem, and significantly improves existing works in terms of F1-score and AUC score, resulting in state-of-the-art performance.

An Asymmetric Contrastive Loss for Handling Imbalanced Datasets

“…Marrakchi et al [ 12 ] and Chen et al [ 13 ] independently adopted supervised CL to combat class imbalance in the medical domain. They both used a two-stage architecture consisting of (1) feature learning using CL, followed by (2) fine-tuning using classification loss.…”

“…In addition, the architecture of the model in which the contrastive losses are implemented is explained. Our proposed asymmetric loss function is novel, while the architecture is obtained from [ 12 , 13 ] with no changes made. Thus, our contribution lies simply in the change of the loss function.…”

“…This is done by ensuring that the model focuses on samples that are harder to classify during model training. Recent studies also unveiled the potential of contrastive learning as a way to combat imbalanced datasets [ 12 , 13 , 14 , 15 ].…”

“…This becomes important when a rare sample has no other positive samples in the mini-batch. To our knowledge, we are the first to modify the supervised version of CL in order to address class imbalance, effectively augmenting several studies performed previously in [ 12 , 13 ]. The proposed ACL is aimed toward improving the effectiveness of the two-stage architecture originally presented in [ 12 , 13 ], especially in the feature learning aspect.…”

“…To our knowledge, we are the first to modify the supervised version of CL in order to address class imbalance, effectively augmenting several studies performed previously in [ 12 , 13 ]. The proposed ACL is aimed toward improving the effectiveness of the two-stage architecture originally presented in [ 12 , 13 ], especially in the feature learning aspect. In addition, the ACL is designed as a generalization of CL, and thus, it provides more flexibility and tuning opportunities as a loss function.…”