Influential Prototypical Networks for Few Shot Learning: A Dermatological Case Study
This work addresses few-shot learning for dermatological image classification, offering an incremental improvement over existing prototypical networks.
The authors tackled the problem of few-shot learning in dermatology by proposing an influential prototypical network (IPNet) that weights support samples based on their influence on the distribution, outperforming baseline models across three benchmark datasets and various classification tasks.
Prototypical network (PN) is a simple yet effective few shot learning strategy. It is a metric-based meta-learning technique where classification is performed by computing Euclidean distances to prototypical representations of each class. Conventional PN attributes equal importance to all samples and generates prototypes by simply averaging the support sample embeddings belonging to each class. In this work, we propose a novel version of PN that attributes weights to support samples corresponding to their influence on the support sample distribution. Influence weights of samples are calculated based on maximum mean discrepancy (MMD) between the mean embeddings of sample distributions including and excluding the sample. Comprehensive evaluation of our proposed influential PN (IPNet) is performed by comparing its performance with other baseline PNs on three different benchmark dermatological datasets. IPNet outperforms all baseline models with compelling results across all three datasets and various N-way, K-shot classification tasks. Findings from cross-domain adaptation experiments further establish the robustness and generalizability of IPNet.