Related papers: This Looks Like Those: Illuminating Prototypical C…

The challenge in learning abstract concepts from images in an unsupervised fashion lies in the required integration of visual perception and generalizable relational reasoning. Moreover, the unsupervised nature of this task makes it…

Prototype-based neural networks offer interpretable predictions by comparing inputs to learned, representative signal patterns anchored in training data. While such models have shown promise in the classification of physiological data, it…

We propose a novel inherently interpretable machine learning method that bases decisions on few relevant examples that we call prototypes. Our method, ProtoAttend, can be integrated into a wide range of neural network architectures…

Concept-based interpretability methods aim to explain deep neural network model predictions using a predefined set of semantic concepts. These methods evaluate a trained model on a new, "probe" dataset and correlate model predictions with…

Visual Question Answering (VQA) is increasingly used in diverse applications ranging from general visual reasoning to safety-critical domains such as medical imaging and autonomous systems, where models must provide not only accurate…

The rapid growth of user-generated text across digital platforms has intensified the need for interpretable models capable of fine-grained text classification and explanation. Existing prototype-based models offer intuitive explanations but…

Image classification is a fundamental computer vision task and an important baseline for deep metric learning. In decades efforts have been made on enhancing image classification accuracy by using deep learning models while less attention…

Neural networks, with powerful nonlinear mapping and classification capabilities, are widely applied in mechanical fault diagnosis to ensure safety. However, being typical black-box models, their application is limited in…

Concept-based explainability methods provide insight into deep learning systems by constructing explanations using human-understandable concepts. While the literature on human reasoning demonstrates that we exploit relationships between…

In this paper we propose a simple yet powerful method for learning representations in supervised learning scenarios where each original input datapoint is described by a set of vectors and their associated outputs may be given by soft…

Deep learning based data-driven approaches have been successfully applied in various image understanding applications ranging from object recognition, semantic segmentation to visual question answering. However, the lack of knowledge…

Models based on human-understandable concepts have received extensive attention to improve model interpretability for trustworthy artificial intelligence in the field of medical image analysis. These methods can provide convincing…

We propose a novel framework for few-shot learning by leveraging large-scale vision-language models such as CLIP. Motivated by unimodal prototypical networks for few-shot learning, we introduce Proto-CLIP which utilizes image prototypes and…

We are born with the ability to learn concepts by comparing diverse observations. This helps us to understand the new world in a compositional manner and facilitates extrapolation, as objects naturally consist of multiple concepts. In this…

Few-shot medical image segmentation has achieved great progress in improving accuracy and efficiency of medical analysis in the biomedical imaging field. However, most existing methods cannot explore inter-class relations among base and…

Recognizing relations between entities is a pivotal task of relational learning. Learning relation representations from distantly-labeled datasets is difficult because of the abundant label noise and complicated expressions in human…

Prototypical self-explainable classifiers have emerged to meet the growing demand for interpretable AI systems. These classifiers are designed to incorporate high transparency in their decisions by basing inference on similarity with…

To facilitate implementation of high-accuracy deep neural networks especially on resource-constrained devices, maintaining low computation requirements is crucial. Using very deep models for classification purposes not only decreases the…

Concept probing has recently gained popularity as a way for humans to peek into what is encoded within artificial neural networks. In concept probing, additional classifiers are trained to map the internal representations of a model into…

Explainability is a longstanding challenge in deep learning, especially in high-stakes domains like healthcare. Common explainability methods highlight image regions that drive an AI model's decision. Humans, however, heavily rely on…