相关论文: CRAFT: Concept Recursive Activation FacTorization …

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…

Aligning Diffusion models has achieved remarkable breakthroughs in generating high-quality, human preference-aligned images. Existing techniques, such as supervised fine-tuning (SFT) and DPO-style preference optimization, have become…

Although saliency maps can highlight important regions to explain the reasoning behind image classification in artificial intelligence (AI), the meaning of these regions is left to the user's interpretation. In contrast, conceptbased…

Motivated by distinct, though related, criteria, a growing number of attribution methods have been developed tointerprete deep learning. While each relies on the interpretability of the concept of "importance" and our ability to visualize…

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…

Concept-based explanations translate the internal representations of deep learning models into a language that humans are familiar with: concepts. One popular method for finding concepts is Concept Activation Vectors (CAVs), which are…

Using attention weights to identify information that is important for models' decision-making is a popular approach to interpret attention-based neural networks. This is commonly realized in practice through the generation of a heat-map for…

Attribution maps are one of the most established tools to explain the functioning of computer vision models. They assign importance scores to input features, indicating how relevant each feature is for the prediction of a deep neural…

Machine learning models that first learn a representation of a domain in terms of human-understandable concepts, then use it to make predictions, have been proposed to facilitate interpretation and interaction with models trained on…

As generative techniques become increasingly accessible, authentic visuals are frequently subjected to iterative alterations by various individuals employing a variety of tools. Currently, to avoid misinformation and ensure accountability,…

Understanding complex machine learning models such as deep neural networks with explanations is crucial in various applications. Many explanations stem from the model perspective, and may not necessarily effectively communicate why the…

In recent years, concept-based approaches have emerged as some of the most promising explainability methods to help us interpret the decisions of Artificial Neural Networks (ANNs). These methods seek to discover intelligible visual…

As large language models are increasingly trained and fine-tuned, practitioners need methods to identify which training data drive specific behaviors, particularly unintended ones. Training Data Attribution (TDA) methods address this by…

Text detection in natural scenes has been a significant and active research subject in computer vision and document analysis because of its wide range of applications as evidenced by the emergence of the Robust Reading Competition. One of…

Interpretability has become an important topic of research as more machine learning (ML) models are deployed and widely used to make important decisions. Most of the current explanation methods provide explanations through feature…

While concept-based interpretability methods have traditionally focused on local explanations of neural network predictions, we propose a novel framework and interactive tool that extends these methods into the domain of mechanistic…

We propose Automatic Feature Explanation using Contrasting Concepts (FALCON), an interpretability framework to explain features of image representations. For a target feature, FALCON captions its highly activating cropped images using a…

Convolutional neural networks have been shown to develop internal representations, which correspond closely to semantically meaningful objects and parts, although trained solely on class labels. Class Activation Mapping (CAM) is a recent…

Diffusion models have shown remarkable abilities in generating realistic and high-quality images from text prompts. However, a trained model remains largely black-box; little do we know about the roles of its components in exhibiting a…

Explaining machine learning (ML) predictions has become crucial as ML models are increasingly deployed in high-stakes domains such as healthcare. While SHapley Additive exPlanations (SHAP) is widely used for model interpretability, it fails…