English
Related papers

Related papers: Probing Classifiers are Unreliable for Concept Rem…

200 papers

Counterfactual Explanations are becoming a de-facto standard in post-hoc interpretable machine learning. For a given classifier and an instance classified in an undesired class, its counterfactual explanation corresponds to small…

Machine Learning · Computer Science 2024-01-17 Veronica Piccialli , Dolores Romero Morales , Cecilia Salvatore

Neural networks are proven to be remarkably successful for classification and diagnosis in medical applications. However, the ambiguity in the decision-making process and the interpretability of the learned features is a matter of concern.…

Computer Vision and Pattern Recognition · Computer Science 2019-08-20 Ashkan Khakzar , Shadi Albarqouni , Nassir Navab

Probing is widely used to study which features can be decoded from language model representations. However, the common decoding probe approach has two limitations that we aim to solve with our new encoding probe approach: contributions of…

Computation and Language · Computer Science 2026-05-04 Gaofei Shen , Martijn Bentum , Tom Lentz , Afra Alishahi , Grzegorz Chrupała

The proliferation of text-to-image diffusion models has raised significant privacy and security concerns, particularly regarding the generation of copyrighted or harmful images. In response, concept erasure (defense) methods have been…

Machine Learning · Computer Science 2025-10-06 Alex D. Richardson , Kaicheng Zhang , Lucas Beerens , Dongdong Chen

Neural networks trained on visual data are well-known to be vulnerable to often imperceptible adversarial perturbations. The reasons for this vulnerability are still being debated in the literature. Recently Ilyas et al. (2019) showed that…

Machine Learning · Computer Science 2021-02-11 Jacob M. Springer , Melanie Mitchell , Garrett T. Kenyon

Despite excellent performance of deep neural networks (DNNs) in image classification, detection, and prediction, characterizing how DNNs make a given decision remains an open problem, resulting in a number of interpretability methods.…

Machine Learning · Computer Science 2023-09-13 Lennart Brocki , Neo Christopher Chung

Deep networks have shown remarkable performance across a wide range of tasks, yet getting a global concept-level understanding of how they function remains a key challenge. Many post-hoc concept-based approaches have been introduced to…

Machine Learning · Computer Science 2026-04-15 Amin Parchami-Araghi , Sukrut Rao , Jonas Fischer , Bernt Schiele

A major challenge in Explainable AI is in correctly interpreting activations of hidden neurons: accurate interpretations would help answer the question of what a deep learning system internally detects as relevant in the input, demystifying…

Artificial Intelligence · Computer Science 2026-02-23 Abhilekha Dalal , Rushrukh Rayan , Adrita Barua , Eugene Y. Vasserman , Md Kamruzzaman Sarker , Pascal Hitzler

Learning an empirically effective model with generalization using limited data is a challenging task for deep neural networks. In this paper, we propose a novel learning framework called PurifiedLearning to exploit task-irrelevant features…

Machine Learning · Computer Science 2022-07-12 Yinghui Li , Chen Wang , Yangning Li , Hai-Tao Zheng , Ying Shen

Recent works have empirically shown that there exist adversarial examples that can be hidden from neural network interpretability (namely, making network interpretation maps visually similar), or interpretability is itself susceptible to…

Machine Learning · Computer Science 2020-10-23 Akhilan Boopathy , Sijia Liu , Gaoyuan Zhang , Cynthia Liu , Pin-Yu Chen , Shiyu Chang , Luca Daniel

Deep neural networks have demonstrated remarkable performance in many data-driven and prediction-oriented applications, and sometimes even perform better than humans. However, their most significant drawback is the lack of interpretability,…

Machine Learning · Computer Science 2023-02-22 Jiahui Li , Kun Kuang , Lin Li , Long Chen , Songyang Zhang , Jian Shao , Jun Xiao

Classifying images with an interpretable decision-making process is a long-standing problem in computer vision. In recent years, Prototypical Part Networks has gained traction as an approach for self-explainable neural networks, due to…

Computer Vision and Pattern Recognition · Computer Science 2025-03-14 Zhijie Zhu , Lei Fan , Maurice Pagnucco , Yang Song

Recent years have witnessed the emergence of a variety of post-hoc interpretations that aim to uncover how natural language processing (NLP) models make predictions. Despite the surge of new interpretation methods, it remains an open…

Computation and Language · Computer Science 2022-04-04 Fan Yin , Zhouxing Shi , Cho-Jui Hsieh , Kai-Wei Chang

By now there is substantial evidence that deep learning models learn certain human-interpretable features as part of their internal representations of data. As having the right (or wrong) concepts is critical to trustworthy machine learning…

Machine Learning · Computer Science 2023-12-29 Nicholas Konz , Charles Godfrey , Madelyn Shapiro , Jonathan Tu , Henry Kvinge , Davis Brown

With the perpetual increase of complexity of the state-of-the-art deep neural networks, it becomes a more and more challenging task to maintain their interpretability. Our work aims to evaluate the effects of adversarial training utilized…

Computer Vision and Pattern Recognition · Computer Science 2023-11-21 Delyan Boychev

The interpretability of model has become one of the obstacles to its wide application in the high-stake fields. The usual way to obtain interpretability is to build a black-box first and then explain it using the post-hoc methods. However,…

Machine Learning · Computer Science 2023-04-04 Zihao Chen , Xiaomeng Wang , Yuanjiang Huang , Tao Jia

Deep neural network can easily overfit to even noisy labels due to its high capacity, which degrades the generalization performance of a model. To overcome this issue, we propose a new approach for learning from noisy labels (LNL) via…

Computer Vision and Pattern Recognition · Computer Science 2023-04-20 Seulki Park , Hwanjun Song , Daeho Um , Dae Ung Jo , Sangdoo Yun , Jin Young Choi

We investigate whether post-hoc model explanations are effective for diagnosing model errors--model debugging. In response to the challenge of explaining a model's prediction, a vast array of explanation methods have been proposed. Despite…

Computer Vision and Pattern Recognition · Computer Science 2020-11-12 Julius Adebayo , Michael Muelly , Ilaria Liccardi , Been Kim

Deep learning models are widely used for image analysis. While they offer high performance in terms of accuracy, people are concerned about if these models inappropriately make inferences using irrelevant features that are not encoded from…

Machine Learning · Computer Science 2021-05-25 Yongqiang Tian , Shiqing Ma , Ming Wen , Yepang Liu , Shing-Chi Cheung , Xiangyu Zhang

The last decade has seen huge progress in the development of advanced machine learning models; however, those models are powerless unless human users can interpret them. Here we show how the mind's construction of concepts and meaning can…

Machine Learning · Statistics 2016-07-04 Nick Condry