Interpretable Concept-based Prototypical Networks for Few-Shot Learning
Few-shot learning aims at recognizing new instances from classes with limited samples. This challenging task is usually alleviated by performing meta-learning on similar tasks. However, the resulting models are black-boxes. There has been growing concerns about deploying black-box machine learning models and FSL is not an exception in this regard. In this paper, we propose a method for FSL based on a set of human-interpretable concepts. It constructs a set of metric spaces associated with the concepts and classifies samples of novel classes by aggregating concept-specific decisions. The proposed method does not require concept annotations for query samples. This interpretable method achieved results on a par with six previously state-of-the-art black-box FSL methods on the CUB fine-grained bird classification dataset.
Code (0)
등록된 구현이 없습니다.
Tasks
Few-Shot LearningMeta-LearningSimilar Papers 제목 키워드 기반
Interpretable Few-Shot Image Classification via Prototypical Concept-Guided Mixture of LoRA Experts
Self-Explainable Models (SEMs) rely on Prototypical Concept Learning (PCL) to enable their visual recognition processes more interpretable, but they often struggle in data-scarce settings where insufficient training samp…
Explainable ModelsFew-Shot Image Classificationimage-classificationImage ClassificationThis Looks Like Those: Illuminating Prototypical Concepts Using Multiple Visualizations
We present ProtoConcepts, a method for interpretable image classification combining deep learning and case-based reasoning using prototypical parts. Existing work in prototype-based image classification uses a "this look…
Eliciting Knowledge from Pretrained Language Models for Prototypical Prompt Verbalizer
Recent advances on prompt-tuning cast few-shot classification tasks as a masked language modeling problem. By wrapping input into a template and using a verbalizer which constructs a mapping between label space and label…
ClassificationContrastive LearningLanguage ModelingLanguage Modelling+3ProtoSeg: Interpretable Semantic Segmentation with Prototypical Parts
We introduce ProtoSeg, a novel model for interpretable semantic image segmentation, which constructs its predictions using similar patches from the training set. To achieve accuracy comparable to baseline methods, we ada…
DiversityImage SegmentationSegmentationSemantic SegmentationThis Probably Looks Exactly Like That: An Invertible Prototypical Network
We combine concept-based neural networks with generative, flow-based classifiers into a novel, intrinsically explainable, exactly invertible approach to supervised learning. Prototypical neural networks, a type of concep…