English
Related papers

Related papers: Self-Interpretable Model with TransformationEquiva…

200 papers

Transformers have significantly advanced the field of natural language processing, but comprehending their internal mechanisms remains a challenge. In this paper, we introduce a novel geometric perspective that elucidates the inner…

Computation and Language · Computer Science 2023-09-20 Raul Molina

Transformer architectures show significant promise for natural language processing. Given that a single pretrained model can be fine-tuned to perform well on many different tasks, these networks appear to extract generally useful linguistic…

Machine Learning · Computer Science 2019-10-29 Andy Coenen , Emily Reif , Ann Yuan , Been Kim , Adam Pearce , Fernanda Viégas , Martin Wattenberg

Multimodal image super-resolution (SR) is the reconstruction of a high resolution image given a low-resolution observation with the aid of another image modality. While existing deep multimodal models do not incorporate domain knowledge…

Computer Vision and Pattern Recognition · Computer Science 2020-09-08 Iman Marivani , Evaggelia Tsiligianni , Bruno Cornelis , Nikos Deligiannis

We formalize a novel modeling framework for achieving interpretability in deep learning, anchored in the principle of inference equivariance. While the direct verification of interpretability scales exponentially with the number of…

Detecting robust keypoints from an image is an integral part of many computer vision problems, and the characteristic orientation and scale of keypoints play an important role for keypoint description and matching. Existing learning-based…

Computer Vision and Pattern Recognition · Computer Science 2022-04-20 Jongmin Lee , Byungjin Kim , Minsu Cho

We present the Topology Transformation Equivariant Representation learning, a general paradigm of self-supervised learning for node representations of graph data to enable the wide applicability of Graph Convolutional Neural Networks…

Machine Learning · Computer Science 2021-12-03 Xiang Gao , Wei Hu , Guo-Jun Qi

Self-supervised learning is a powerful paradigm for representation learning on unlabelled images. A wealth of effective new methods based on instance matching rely on data-augmentation to drive learning, and these have reached a rough…

Computer Vision and Pattern Recognition · Computer Science 2022-10-11 Linus Ericsson , Henry Gouk , Timothy M. Hospedales

Real-world geometry and 3D vision tasks are replete with challenging symmetries that defy tractable analytical expression. In this paper, we introduce Neural Isometries, an autoencoder framework which learns to map the observation space to…

Computer Vision and Pattern Recognition · Computer Science 2024-10-31 Thomas W. Mitchel , Michael Taylor , Vincent Sitzmann

Convolutional neural networks (CNNs) are inherently equivariant to translation. Efforts to embed other forms of equivariance have concentrated solely on rotation. We expand the notion of equivariance in CNNs through the Polar Transformer…

Computer Vision and Pattern Recognition · Computer Science 2018-02-02 Carlos Esteves , Christine Allen-Blanchette , Xiaowei Zhou , Kostas Daniilidis

Although researchers' attention is more focused on the performance of Transformer models, the interpretation of Transformer can never be ignored. Gradient is widely utilized in Transformer interpretation. From the perspective of attention…

Artificial Intelligence · Computer Science 2026-05-13 Yongjin Cui , Xiaohui Fan , Huajun Chen

Interpretability of deep learning is widely used to evaluate the reliability of medical imaging models and reduce the risks of inaccurate patient recommendations. For models exceeding human performance, e.g. predicting RNA structure from…

Quantitative Methods · Quantitative Biology 2022-08-31 Mara Graziani , Niccolò Marini , Nicolas Deutschmann , Nikita Janakarajan , Henning Müller , María Rodríguez Martínez

Simulation-based inference with conditional neural density estimators is a powerful approach to solving inverse problems in science. However, these methods typically treat the underlying forward model as a black box, with no way to exploit…

Machine Learning · Computer Science 2023-05-31 Maximilian Dax , Stephen R. Green , Jonathan Gair , Michael Deistler , Bernhard Schölkopf , Jakob H. Macke

Explainability is a highly demanded requirement for applications in high-risk areas such as medicine. Vision Transformers have mainly been limited to attention extraction to provide insight into the model's reasoning. Our approach combines…

Computer Vision and Pattern Recognition · Computer Science 2025-02-14 Luisa Gallée , Catharina Silvia Lisson , Meinrad Beer , Michael Götz

Convolutional neural networks (CNNs) have been widely utilized in many computer vision tasks. However, CNNs have a fixed reception field and lack the ability of long-range perception, which is crucial to human pose estimation. Due to its…

Computer Vision and Pattern Recognition · Computer Science 2022-06-28 Zinan Xiong , Chenxi Wang , Ying Li , Yan Luo , Yu Cao

Vision Transformers (ViTs) have gained rapid adoption in computational pathology for their ability to model long-range dependencies through self-attention, addressing the limitations of convolutional neural networks that excel at local…

Image and Video Processing · Electrical Eng. & Systems 2026-01-15 Fuyao Chen , Yuexi Du , Elèonore V. Lieffrig , Nicha C. Dvornek , John A. Onofrey

This paper argues that interpretability research in Artificial Intelligence (AI) is fundamentally ill-posed as existing definitions of interpretability fail to describe how interpretability can be formally tested or designed for. We posit…

Artificial Intelligence · Computer Science 2026-01-30 Pietro Barbiero , Mateo Espinosa Zarlenga , Francesco Giannini , Alberto Termine , Filippo Bonchi , Mateja Jamnik , Giuseppe Marra

In many real-world applications of regression, conditional probability estimation, and uncertainty quantification, exploiting symmetries rooted in physics or geometry can dramatically improve generalization and sample efficiency. While…

Machine Learning · Computer Science 2025-05-28 Daniel Ordoñez-Apraez , Vladimir Kostić , Alek Fröhlich , Vivien Brandt , Karim Lounici , Massimiliano Pontil

Machine learning models are exceptionally effective in capturing complex non-linear relationships of high-dimensional datasets and making accurate predictions. However, their intrinsic ``black-box'' nature makes it difficult to interpret…

Plasma Physics · Physics 2024-07-29 Tadas Pyragius , Cary Colgan , Hazel Lowe , Filip Janky , Matteo Fontana , Yichen Cai , Graham Naylor

The impressive capabilities of deep learning models are often counterbalanced by their inherent opacity, commonly termed the "black box" problem, which impedes their widespread acceptance in high-trust domains. In response, the intersecting…

Machine Learning · Computer Science 2025-09-16 Mitali Raj

Supervised machine learning models boast remarkable predictive capabilities. But can you trust your model? Will it work in deployment? What else can it tell you about the world? We want models to be not only good, but interpretable. And yet…

Machine Learning · Computer Science 2017-03-07 Zachary C. Lipton