Related papers: TextCAVs: Debugging vision models using text

Concept activation vector (CAV) has attracted broad research interest in explainable AI, by elegantly attributing model predictions to specific concepts. However, the training of CAV often necessitates a large number of high-quality images,…

In safety-critical applications, practitioners are reluctant to trust neural networks when no interpretable explanations are available. Many attempts to provide such explanations revolve around pixel-based attributions or use previously…

Convolutional Neural Networks (CNNs) have seen significant performance improvements in recent years. However, due to their size and complexity, they function as black-boxes, leading to transparency concerns. State-of-the-art saliency…

Advances in multi-modal embeddings, and in particular CLIP, have recently driven several breakthroughs in Computer Vision (CV). CLIP has shown impressive performance on a variety of tasks, yet, its inherently opaque architecture may hinder…

Our understanding of the visual world is centered around various concept axes, characterizing different aspects of visual entities. While different concept axes can be easily specified by language, e.g. color, the exact visual nuances along…

Interpreting the inner workings of deep learning models is crucial for establishing trust and ensuring model safety. Concept-based explanations have emerged as a superior approach that is more interpretable than feature attribution…

The analysis of vision-based deep neural networks (DNNs) is highly desirable but it is very challenging due to the difficulty of expressing formal specifications for vision tasks and the lack of efficient verification procedures. In this…

An essential step in deploying medical imaging models is ensuring alignment with clinical knowledge and interpretability. We focus on mapping clinical concepts into the latent space of generative models to identify Concept Activation…

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…

Deep learning models are widely used in critical applications, highlighting the need for pre-deployment model understanding and improvement. Visual concept-based methods, while increasingly used for this purpose, face challenges: (1) most…

With a growing interest in understanding neural network prediction strategies, Concept Activation Vectors (CAVs) have emerged as a popular tool for modeling human-understandable concepts in the latent space. Commonly, CAVs are computed by…

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…

We study the problem of concept induction in visual reasoning, i.e., identifying concepts and their hierarchical relationships from question-answer pairs associated with images; and achieve an interpretable model via working on the induced…

Concept Activation Vectors (CAVs) are a tool from explainable AI, offering a promising approach for understanding how human-understandable concepts are encoded in a model's latent spaces. They are computed from hidden-layer activations of…

Multimodal pre-trained models, such as CLIP, are popular for zero-shot classification due to their open-vocabulary flexibility and high performance. However, vision-language models, which compute similarity scores between images and class…

Utilizing potent representations of the large vision-language models (VLMs) to accomplish various downstream tasks has attracted increasing attention. Within this research field, soft prompt learning has become a representative approach for…

Concept-based explainable approaches have emerged as a promising method in explainable AI because they can interpret models in a way that aligns with human reasoning. However, their adaption in the text domain remains limited. Most existing…

Medical image classification is a critical problem for healthcare, with the potential to alleviate the workload of doctors and facilitate diagnoses of patients. However, two challenges arise when deploying deep learning models to real-world…

Large-scale pre-trained Vision-Language Models (VLMs), such as CLIP, establish the correlation between texts and images, achieving remarkable success on various downstream tasks with fine-tuning. In existing fine-tuning methods, the…

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…