English
Related papers

Related papers: Gauge-invariant representation holonomy

200 papers

Image denoising is of vital importance in many imaging or computer vision related areas. With the convolutional neural networks showing strong capability in computer vision tasks, the performance of image denoising has also been brought up…

Computer Vision and Pattern Recognition · Computer Science 2021-12-23 Zhuang Jia

Euclidean deep learning is often inadequate for addressing real-world signals where the representation space is irregular and curved with complex topologies. Interpreting the geometric properties of such feature spaces has become paramount…

Computer Vision and Pattern Recognition · Computer Science 2024-09-12 Ramzan Basheer , Deepak Mishra

Convolutional neural networks (CNNs) have achieved state-of-the-art results on many visual recognition tasks. However, current CNN models still exhibit a poor ability to be invariant to spatial transformations of images. Intuitively, with…

Computer Vision and Pattern Recognition · Computer Science 2019-12-04 Xu Shen , Xinmei Tian , Anfeng He , Shaoyan Sun , Dacheng Tao

This work explores the ability of computer vision algorithms to characterise dark matter haloes formed in different models of structure formation. We produce surface mass density maps of the most massive haloes in a suite of eight numerical…

Cosmology and Nongalactic Astrophysics · Physics 2017-04-19 Julian Merten , Quim Llorens , Hans Winther

Despite the success of fine-tuning pretrained language encoders like BERT for downstream natural language understanding (NLU) tasks, it is still poorly understood how neural networks change after fine-tuning. In this work, we use centered…

Computation and Language · Computer Science 2021-09-21 Jason Phang , Haokun Liu , Samuel R. Bowman

Many learning problems involve symmetries, and while invariance can be built into neural architectures, it can also emerge implicitly when training on group-structured data. We study this phenomenon in classical Hopfield networks and show…

Machine Learning · Computer Science 2026-01-21 Michael Murray , Tenzin Chan , Kedar Karhadker , Christopher J. Hillar

In both artificial and biological systems, the centered kernel alignment (CKA) has become a widely used tool for quantifying neural representation similarity. While current CKA estimators typically correct for the effects of finite stimuli…

Neurons and Cognition · Quantitative Biology 2025-02-26 Chanwoo Chun , Abdulkadir Canatar , SueYeon Chung , Daniel D. Lee

To overcome the restriction of identical distribution assumption, invariant representation learning for unsupervised domain adaptation (UDA) has made significant advances in computer vision and pattern recognition communities. In UDA…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 You-Wei Luo , Chuan-Xian Ren , Xiao-Lin Xu , Qingshan Liu

Graph convolution networks (GCNs) have been enormously successful in learning representations over several graph-based machine learning tasks. Specific to learning rich node representations, most of the methods have solely relied on the…

Machine Learning · Computer Science 2022-11-03 Ashish Tiwari , Sresth Tosniwal , Shanmuganathan Raman

We introduce the holonomy-diffeomorphism algebra, a C*-algebra generated by flows of vectorfields and the compactly supported smooth functions on a manifold. We show that the separable representations of the holonomy-diffeomorphism algebra…

Mathematical Physics · Physics 2013-01-08 Johannes Aastrup , Jesper M. Grimstrup

Topological invariants allow to characterize Hamiltonians, predicting the existence of topologically protected in-gap modes. Those invariants can be computed by tracing the evolution of the occupied wavefunctions under twisted boundary…

Mesoscale and Nanoscale Physics · Physics 2018-04-04 D. Carvalho , N. A. Garcia-Martinez , J. L. Lado , J. Fernandez-Rossier

Representation learning is at the heart of what makes deep learning effective. In this work, we introduce a new framework for representation learning that we call "Holographic Neural Architectures" (HNAs). In the same way that an observer…

Machine Learning · Statistics 2018-06-05 Tariq Daouda , Jeremie Zumer , Claude Perreault , Sébastien Lemieux

The goal of gait recognition is to extract identity-invariant features of an individual under various gait conditions, e.g., cross-view and cross-clothing. Most gait models strive to implicitly learn the common traits across different gait…

Computer Vision and Pattern Recognition · Computer Science 2026-01-12 Zengbin Wang , Junjie Li , Saihui Hou , Xu Liu , Chunshui Cao , Yongzhen Huang , Muyi Sun , Siye Wang , Man Zhang

For Cartan geometries admitting automorphisms with isotropies satisfying a particular, loosely dynamical property on their model geometries, we demonstrate the existence of an open subset of the geometry with trivial holonomy. This…

Differential Geometry · Mathematics 2025-04-22 Jacob W. Erickson

Over the past decade, deep learning has proven to be a highly effective tool for learning meaningful features from raw data. However, it remains an open question how deep networks perform hierarchical feature learning across layers. In this…

Machine Learning · Computer Science 2025-11-17 Peng Wang , Xiao Li , Can Yaras , Zhihui Zhu , Laura Balzano , Wei Hu , Qing Qu

Assumptions about invariances or symmetries in data can significantly increase the predictive power of statistical models. Many commonly used models in machine learning are constraint to respect certain symmetries in the data, such as…

Machine Learning · Statistics 2022-08-03 Tycho F. A. van der Ouderaa , Mark van der Wilk

Translating or rotating an input image should not affect the results of many computer vision tasks. Convolutional neural networks (CNNs) are already translation equivariant: input image translations produce proportionate feature map…

Computer Vision and Pattern Recognition · Computer Science 2017-04-12 Daniel E. Worrall , Stephan J. Garbin , Daniyar Turmukhambetov , Gabriel J. Brostow

Training a Convolutional Neural Network (CNN) to be robust against rotation has mostly been done with data augmentation. In this paper, another progressive vision of research direction is highlighted to encourage less dependence on data…

Computer Vision and Pattern Recognition · Computer Science 2021-10-22 Sungwon Hwang , Hyungtae Lim , Hyun Myung

For a large class of feature maps we provide a tight asymptotic characterisation of the test error associated with learning the readout layer, in the high-dimensional limit where the input dimension, hidden layer widths, and number of…

Machine Learning · Statistics 2024-06-11 Dominik Schröder , Daniil Dmitriev , Hugo Cui , Bruno Loureiro

Unlike standard object classification, where the image to be classified contains one or multiple instances of the same object, indoor scene classification is quite different since the image consists of multiple distinct objects. Further,…

Computer Vision and Pattern Recognition · Computer Science 2016-11-03 Munawar Hayat , Salman H. Khan , Mohammed Bennamoun , Senjian An