Influential Prototypical Networks for Few Shot Learning: A Dermatological Case Study
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain AdaptationFew-Shot LearningMeta-LearningSimilar Papers 제목 키워드 기반
Prototypical Clustering Networks for Dermatological Disease Diagnosis
We consider the problem of image classification for the purpose of aiding doctors in dermatological diagnosis. Dermatological diagnosis poses two major challenges for standard off-the-shelf techniques: First, the data di…
ClusteringGeneral Classificationimage-classificationImage ClassificationIPNET:Influential Prototypical Networks for Few Shot Learning
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 representati…
Few-Shot LearningMeta-LearningLearning to Classify Intents and Slot Labels Given a Handful of Examples
Intent classification (IC) and slot filling (SF) are core components in most goal-oriented dialogue systems. Current IC/SF models perform poorly when the number of training examples per class is small. We propose a new f…
Few-Shot LearningGoal-Oriented Dialogue Systemsintent-classificationIntent Classification+3MAKE: Multi-Aspect Knowledge-Enhanced Vision-Language Pretraining for Zero-shot Dermatological Assessment
Dermatological diagnosis represents a complex multimodal challenge that requires integrating visual features with specialized clinical knowledge. While vision-language pretraining (VLP) has advanced medical AI, its effec…
Clinical KnowledgeContrastive LearningCross-Modal RetrievalSemi-Supervised Few-Shot Learning with Prototypical Random Walks
Recent progress has shown that few-shot learning can be improved with access to unlabelled data, known as semi-supervised few-shot learning(SS-FSL). We introduce an SS-FSL approach, dubbed as Prototypical Random Walk Net…
Few-Shot Learning