Revisiting the Shape-Bias of Deep Learning for Dermoscopic Skin Lesion Classification
This work addresses the problem of improving skin lesion classification models for medical diagnosis by challenging the prevalent shape-bias assumption, showing it is incremental as it builds on existing human vision alignment research.
The paper revisits the assumption that shape-biased models improve robustness in skin lesion classification, finding that datasets vary in feature biases and complex feature combinations beyond shape are often more effective, with shape-biasing sometimes even reducing performance.
It is generally believed that the human visual system is biased towards the recognition of shapes rather than textures. This assumption has led to a growing body of work aiming to align deep models' decision-making processes with the fundamental properties of human vision. The reliance on shape features is primarily expected to improve the robustness of these models under covariate shift. In this paper, we revisit the significance of shape-biases for the classification of skin lesion images. Our analysis shows that different skin lesion datasets exhibit varying biases towards individual image features. Interestingly, despite deep feature extractors being inclined towards learning entangled features for skin lesion classification, individual features can still be decoded from this entangled representation. This indicates that these features are still represented in the learnt embedding spaces of the models, but not used for classification. In addition, the spectral analysis of different datasets shows that in contrast to common visual recognition, dermoscopic skin lesion classification, by nature, is reliant on complex feature combinations beyond shape-bias. As a natural consequence, shifting away from the prevalent desire of shape-biasing models can even improve skin lesion classifiers in some cases.