R Marcinkevičs, JE Vogt - Wiley Interdisciplinary Reviews: Data …, 2023 - Wiley Online Library
Interpretability and explainability are crucial for machine learning (ML) and statistical applications in medicine, economics, law, and natural sciences and form an essential …
H Chefer, S Gur, L Wolf - … of the IEEE/CVF conference on …, 2021 - openaccess.thecvf.com
Self-attention techniques, and specifically Transformers, are dominating the field of text processing and are becoming increasingly popular in computer vision classification tasks. In …
B Wu, H Chen, M Zhang, Z Zhu, S Wei… - Advances in …, 2022 - proceedings.neurips.cc
Backdoor learning is an emerging and vital topic for studying deep neural networks' vulnerability (DNNs). Many pioneering backdoor attack and defense methods are being …
H Chefer, S Gur, L Wolf - Proceedings of the IEEE/CVF …, 2021 - openaccess.thecvf.com
Transformers are increasingly dominating multi-modal reasoning tasks, such as visual question answering, achieving state-of-the-art results thanks to their ability to contextualize …
Abstract Visual Counterfactual Explanations (VCEs) are an important tool to understand the decisions of an image classifier. They are “small” but “realistic” semantic changes of the …
A critical problem in the field of post hoc explainability is the lack of a common foundational goal among methods. For example, some methods are motivated by function approximation …
Transformers have become an important workhorse of machine learning, with numerous applications. This necessitates the development of reliable methods for increasing their …
C Zhao, C Wang, G Hu, H Chen, C Liu… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
With the rapid development of Deepfake synthesis technology, our information security and personal privacy have been severely threatened in recent years. To achieve a robust …
Despite a sea of interpretability methods that can produce plausible explanations, the field has also empirically seen many failure cases of such methods. In light of these results, it …