相关论文: This Looks Like Those: Illuminating Prototypical C…

Prototypical methods have recently gained a lot of attention due to their intrinsic interpretable nature, which is obtained through the prototypes. With growing use cases of model reuse and distillation, there is a need to also study…

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…

Concept-based interpretability methods are a popular form of explanation for deep learning models which provide explanations in the form of high-level human interpretable concepts. These methods typically find concept activation vectors…

The increasing impact of black box models, and particularly of unsupervised ones, comes with an increasing interest in tools to understand and interpret them. In this paper, we consider in particular how to characterise visual groupings…

Robotic agents need to understand how to interact with objects in their environment, both autonomously and during human-robot interactions. Affordance detection on 3D point clouds, which identifies object regions that allow specific…

Exploring and understanding efficient image representations is a long-standing challenge in computer vision. While deep learning has achieved remarkable progress across image understanding tasks, its internal representations are often…

Is analogical reasoning a task that must be learned to solve from scratch by applying deep learning models to massive numbers of reasoning problems? Or are analogies solved by computing similarities between structured representations of…

This work explores enabling Chain-of-Thought (CoT) reasoning to link visual cues across multiple images. A straightforward solution is to adapt rule-based reinforcement learning for Vision-Language Models (VLMs). However, such methods…

Concept-based models aim to explain model decisions with human-understandable concepts. However, most existing approaches treat concepts as numerical attributes, without providing complementary visual explanations that could localize the…

Prototype-based methods are of the particular interest for domain specialists and practitioners as they summarize a dataset by a small set of representatives. Therefore, in a classification setting, interpretability of the prototypes is as…

Although explainability is essential in the clinical diagnosis, most deep learning models still function as black boxes without elucidating their decision-making process. In this study, we investigate the explainable model development that…

Part-prototype networks (e.g., ProtoPNet, ProtoTree, and ProtoPool) have attracted broad research interest for their intrinsic interpretability and comparable accuracy to non-interpretable counterparts. However, recent works find that the…

We develop an approach to learning visual representations that embraces multimodal data, driven by a combination of intra- and inter-modal similarity preservation objectives. Unlike existing visual pre-training methods, which solve a proxy…

Prototype-based classification learning methods are known to be inherently interpretable. However, this paradigm suffers from major limitations compared to deep models, such as lower performance. This led to the development of the so-called…

Graph Neural Networks (GNNs) have shown great ability in modeling graph-structured data for various domains. However, GNNs are known as black-box models that lack interpretability. Without understanding their inner working, we cannot fully…

Deep neural networks are often considered opaque systems, prompting the need for explainability methods to improve trust and accountability. Existing approaches typically attribute test-time predictions either to input features (e.g.,…

This paper presents Discriminative Part Network (DP-Net), a deep architecture with strong interpretation capabilities, which exploits a pretrained Convolutional Neural Network (CNN) combined with a part-based recognition module. This system…

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…

Word Embeddings are used widely in multiple Natural Language Processing (NLP) applications. They are coordinates associated with each word in a dictionary, inferred from statistical properties of these words in a large corpus. In this paper…

Concept Bottleneck Models (CBMs) offer interpretable alternatives to black-box predictors by introducing human-relatable concepts before the final output. However, existing CBMs struggle to verify whether predicted concepts correspond to…