相关论文: MAPS: Masked Attribution-based Probing of Strategi…

Developments in machine learning interpretability techniques over the past decade have provided new tools to observe the image regions that are most informative for classification and localization in artificial neural networks (ANNs). Are…

Explainable AI aims to render model behavior understandable by humans, which can be seen as an intermediate step in extracting causal relations from correlative patterns. Due to the high risk of possible fatal decisions in image-based…

Convolutional Neural Networks (CNN) have become de fact state-of-the-art for the main computer vision tasks. However, due to the complex underlying structure their decisions are hard to understand which limits their use in some context of…

Modern vision models achieve strong performance on standard benchmarks, yet their aggregate accuracy reveals little about which scene properties drive their predictions. Existing robustness benchmarks provide important stress tests, but…

Alignment between human brain networks and artificial models has become an active research area in vision science and machine learning. A widely adopted approach is identifying "metamers," stimuli physically different yet perceptually…

Explaining deep learning models in a way that humans can easily understand is essential for responsible artificial intelligence applications. Attribution methods constitute an important area of explainable deep learning. The attribution…

Existing self-supervised learning methods based on contrastive learning and masked image modeling have demonstrated impressive performances. However, current masked image modeling methods are mainly utilized in natural images, and their…

Text-based person search (TBPS) is a problem that gained significant interest within the research community. The task is that of retrieving one or more images of a specific individual based on a textual description. The multi-modal nature…

Explaining recommendations enables users to understand whether recommended items are relevant to their needs and has been shown to increase their trust in the system. More generally, if designing explainable machine learning models is key…

Personalized product search aims to retrieve and rank items that match users' preferences and search intent. Despite their effectiveness, existing approaches typically assume that users' query fully captures their real motivation. However,…

A fundamental problem in modern supervised learning is computing reliable conditional prediction intervals in high-dimensional settings: existing methods often rely on restrictive modelling assumptions, do not scale as predictor dimension…

A multitude of explainability methods and associated fidelity performance metrics have been proposed to help better understand how modern AI systems make decisions. However, much of the current work has remained theoretical -- without much…

Human reasoning is grounded in an ability to identify highly abstract commonalities governing superficially dissimilar visual inputs. Recent efforts to develop algorithms with this capacity have largely focused on approaches that require…

Masking strategies commonly employed in natural language processing are still underexplored in vision tasks such as concept learning, where conventional methods typically rely on full images. However, using masked images diversifies…

To make sense of their surroundings, intelligent systems must transform complex sensory inputs to structured codes that are reduced to task-relevant information such as object category. Biological agents achieve this in a largely autonomous…

We introduce LAMP (Local Attribution Mapping Probe), a method that shines light onto a black-box language model's decision surface and studies how reliably a model maps its stated reasons to its reported predictions by approximating a…

As an emerging field in Machine Learning, Explainable AI (XAI) has been offering remarkable performance in interpreting the decisions made by Convolutional Neural Networks (CNNs). To achieve visual explanations for CNNs, methods based on…

Developing a suitable Deep Neural Network (DNN) often requires significant iteration, where different model versions are evaluated and compared. While metrics such as accuracy are a powerful means to succinctly describe a model's…

Making sense of the world and acting in it relies on building simplified mental representations that abstract away aspects of reality. This principle of cognitive mapping is universal to agents with limited resources. Living organisms,…

Attention heads are one of the building blocks of large language models (LLMs). Prior work on investigating their operation mostly focused on analyzing their behavior during inference for specific circuits or tasks. In this work, we seek a…