ProtoS-ViT: Visual foundation models for sparse self-explainable classifications
Prototypical networks aim to build intrinsically explainable models based on the linear summation of concepts. Concepts are coherent entities that we, as humans, can recognize and associate with a certain object or entity. However, important challenges remain in the fair evaluation of explanation quality provided by these models. This work first proposes an extensive set of quantitative and qualitative metrics which allow to identify drawbacks in current prototypical networks. It then introduces a novel architecture which provides compact explanations, outperforming current prototypical models in terms of explanation quality. Overall, the proposed architecture demonstrates how frozen pre-trained ViT backbones can be effectively turned into prototypical models for both general and domain-specific tasks, in our case biomedical image classifiers. Code is available at \url{https://github.com/hturbe/protosvit}.
Code (1)
Tasks
Explainable ModelsMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
ProtoShotXAI: Using Prototypical Few-Shot Architecture for Explainable AI
Unexplainable black-box models create scenarios where anomalies cause deleterious responses, thus creating unacceptable risks. These risks have motivated the field of eXplainable Artificial Intelligence (XAI) to improve …
Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)ProtoSAM: One-Shot Medical Image Segmentation With Foundational Models
This work introduces a new framework, ProtoSAM, for one-shot medical image segmentation. It combines the use of prototypical networks, known for few-shot segmentation, with SAM - a natural image foundation model. The met…
Image SegmentationMedical Image SegmentationSegmentationSemantic SegmentationProtoSSL: Interpretable Prototype Learning from Unlabeled Time-Series Data
In time-series domains where both predictive performance and interpretability are essential, deep neural networks achieve strong results but provide limited insight into how their predictions are made. Projection-based p…
Audio ClassificationMeta-learners for few-shot weakly-supervised optic disc and cup segmentation on fundus images
This study develops meta-learners for few-shot weakly-supervised segmentation (FWS) to address the challenge of optic disc (OD) and optic cup (OC) segmentation for glaucoma diagnosis with limited labeled fundus images. W…
Unsupervised Domain AdaptationFrom Confusion to Clarity: ProtoScore -- A Framework for Evaluating Prototype-Based XAI
The complexity and opacity of neural networks (NNs) pose significant challenges, particularly in high-stakes fields such as healthcare, finance, and law, where understanding decision-making processes is crucial. To addre…