English
Related papers

Related papers: Invertible Concept-based Explanations for CNN Mode…

200 papers

This paper evaluates whether training a decision tree based on concepts extracted from a concept-based explainer can increase interpretability for Convolutional Neural Networks (CNNs) models and boost the fidelity and performance of the…

Computer Vision and Pattern Recognition · Computer Science 2022-11-22 Gayda Mutahar , Tim Miller

The interpretation of deep learning models is a challenge due to their size, complexity, and often opaque internal state. In addition, many systems, such as image classifiers, operate on low-level features rather than high-level concepts.…

Machine Learning · Statistics 2019-04-05 Been Kim , Martin Wattenberg , Justin Gilmer , Carrie Cai , James Wexler , Fernanda Viegas , Rory Sayres

Convolutional neural networks (CNNs) have succeeded remarkably in various computer vision tasks. However, they are not intrinsically explainable. While the feature-level understanding of CNNs reveals where the models looked, concept-based…

Computer Vision and Pattern Recognition · Computer Science 2025-03-27 Ugochukwu Ejike Akpudo , Yongsheng Gao , Jun Zhou , Andrew Lewis

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…

Machine Learning · Computer Science 2025-02-14 Angus Nicolson , Lisa Schut , J. Alison Noble , Yarin Gal

Deep learning models in computer vision have made remarkable progress, but their lack of transparency and interpretability remains a challenge. The development of explainable AI can enhance the understanding and performance of these models.…

Computer Vision and Pattern Recognition · Computer Science 2025-01-14 Bismillah Khan , Syed Ali Tariq , Tehseen Zia , Muhammad Ahsan , David Windridge

Concept Activation Vectors (CAVs) provide a powerful approach for interpreting deep neural networks by quantifying their sensitivity to human-defined concepts. However, when computed independently at different layers, CAVs often exhibit…

Computer Vision and Pattern Recognition · Computer Science 2025-09-11 Zhenghao He , Sanchit Sinha , Guangzhi Xiong , Aidong Zhang

Concepts such as objects, patterns, and shapes are how humans understand the world. Building on this intuition, concept-based explainability methods aim to study representations learned by deep neural networks in relation to…

Machine Learning · Computer Science 2025-05-26 Laines Schmalwasser , Niklas Penzel , Joachim Denzler , Julia Niebling

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…

Machine Learning · Statistics 2026-01-28 Ekkehard Schnoor , Malik Tiomoko , Jawher Said , Alex Jung , Wojciech Samek

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…

Machine Learning · Computer Science 2022-02-28 Chih-Kuan Yeh , Been Kim , Pradeep Ravikumar

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…

Computer Vision and Pattern Recognition · Computer Science 2025-05-08 Frederik Pahde , Maximilian Dreyer , Leander Weber , Moritz Weckbecker , Christopher J. Anders , Thomas Wiegand , Wojciech Samek , Sebastian Lapuschkin

Concept Activation Vectors (CAVs) offer insights into neural network decision-making by linking human friendly concepts to the model's internal feature extraction process. However, when a new set of CAVs is discovered, they must still be…

Computer Vision and Pattern Recognition · Computer Science 2024-10-24 Laines Schmalwasser , Jakob Gawlikowski , Joachim Denzler , Julia Niebling

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…

Computer Vision and Pattern Recognition · Computer Science 2025-06-04 Antonio De Santis , Riccardo Campi , Matteo Bianchi , Marco Brambilla

To equip Convolutional Neural Networks (CNNs) with explainability, it is essential to interpret how opaque models take specific decisions, understand what causes the errors, improve the architecture design, and identify unethical biases in…

Computer Vision and Pattern Recognition · Computer Science 2024-02-23 Mohammad Mahdi Dehshibi , Mona Ashtari-Majlan , Gereziher Adhane , David Masip

Concept-based interpretations of black-box models are often more intuitive for humans to understand. The most widely adopted approach for concept-based interpretation is Concept Activation Vector (CAV). CAV relies on learning a linear…

Machine Learning · Computer Science 2024-02-07 Andrew Bai , Chih-Kuan Yeh , Pradeep Ravikumar , Neil Y. C. Lin , Cho-Jui Hsieh

Visual interpretability of Convolutional Neural Networks (CNNs) has gained significant popularity because of the great challenges that CNN complexity imposes to understanding their inner workings. Although many techniques have been proposed…

Computer Vision and Pattern Recognition · Computer Science 2021-02-01 Alexandros Stergiou

Deep Neural Networks have often been called the black box because of the complex, deep architecture and non-transparency presented by the inner layers. There is a lack of trust to use Artificial Intelligence in critical and high-precision…

Computer Vision and Pattern Recognition · Computer Science 2024-03-12 Frincy Clement , Ji Yang , Irene Cheng

How can we understand classification decisions made by deep neural networks? Many existing explainability methods rely solely on correlations and fail to account for confounding, which may result in potentially misleading explanations. To…

Machine Learning · Computer Science 2020-03-02 Yash Goyal , Amir Feder , Uri Shalit , Been Kim

Deep learning models suffer from opaqueness. For Convolutional Neural Networks (CNNs), current research strategies for explaining models focus on the target classes within the associated training dataset. As a result, the understanding of…

Computer Vision and Pattern Recognition · Computer Science 2021-02-23 Xuehao Liu , Sarah Jane Delany , Susan McKeever

To tackle increasingly complex tasks, it has become an essential ability of neural networks to learn abstract representations. These task-specific representations and, particularly, the invariances they capture turn neural networks into…

Computer Vision and Pattern Recognition · Computer Science 2020-08-06 Robin Rombach , Patrick Esser , Björn Ommer

Deep convolutional networks have been quite successful at various image classification tasks. The current methods to explain the predictions of a pre-trained model rely on gradient information, often resulting in saliency maps that focus on…

Machine Learning · Computer Science 2020-11-04 Ashish Kumar , Karan Sehgal , Prerna Garg , Vidhya Kamakshi , Narayanan C Krishnan
‹ Prev 1 2 3 10 Next ›