Properties Of Winning Tickets On Skin Lesion Classification
This work addresses the problem of reducing model size for skin cancer detection, which could aid clinicians, but it is incremental as it applies an existing pruning method to a new domain.
The paper applied the Lottery Ticket Hypothesis pruning technique to skin lesion classification, finding that iterative pruning improved accuracy over the unpruned network and resulted in a smaller model for inference, with accuracy gains varying across demographic subgroups like gender and age.
Skin cancer affects a large population every year -- automated skin cancer detection algorithms can thus greatly help clinicians. Prior efforts involving deep learning models have high detection accuracy. However, most of the models have a large number of parameters, with some works even using an ensemble of models to achieve good accuracy. In this paper, we investigate a recently proposed pruning technique called Lottery Ticket Hypothesis. We find that iterative pruning of the network resulted in improved accuracy, compared to that of the unpruned network, implying that -- the lottery ticket hypothesis can be applied to the problem of skin cancer detection and this hypothesis can result in a smaller network for inference. We also examine the accuracy across sub-groups -- created by gender and age -- and it was found that some sub-groups show a larger increase in accuracy than others.