English
Related papers

Related papers: Quantised Transforming Auto-Encoders: Achieving Eq…

200 papers

Transformationally invariant processors constructed by transformed input vectors or operators have been suggested and applied to many applications. In this study, transformationally identical processing based on combining results of all…

Computer Vision and Pattern Recognition · Computer Science 2018-08-21 ShihChung B. Lo , Matthew T. Freedman , Seong K. Mun

Although Convolutional Neural Networks (CNNs) are widely used, their translation invariance (ability to deal with translated inputs) is still subject to some controversy. We explore this question using translation-sensitivity maps to…

Machine Learning · Computer Science 2021-04-20 Johannes C. Myburgh , Coenraad Mouton , Marelie H. Davel

Humans can identify objects following various spatial transformations such as scale and viewpoint. This extends to novel objects, after a single presentation at a single pose, sometimes referred to as online invariance. CNNs have been…

Computer Vision and Pattern Recognition · Computer Science 2022-04-05 Valerio Biscione , Jeffrey S. Bowers

Image translation with convolutional neural networks has recently been used as an approach to multimodal change detection. Existing approaches train the networks by exploiting supervised information of the change areas, which, however, is…

CoVariance Neural Networks (VNNs) perform convolutions on the graph determined by the covariance matrix of the data, which enables expressive and stable covariance-based learning. However, covariance matrices are typically dense, fail to…

Machine Learning · Computer Science 2026-01-21 Andrea Cavallo , Samuel Rey , Antonio G. Marques , Elvin Isufi

Encoding the scale information explicitly into the representation learned by a convolutional neural network (CNN) is beneficial for many computer vision tasks especially when dealing with multiscale inputs. We study, in this paper, a…

Machine Learning · Computer Science 2022-02-08 Wei Zhu , Qiang Qiu , Robert Calderbank , Guillermo Sapiro , Xiuyuan Cheng

We propose the first general framework to automatically correct different types of geometric distortion in a single input image. Our proposed method employs convolutional neural networks (CNNs) trained by using a large synthetic distortion…

Computer Vision and Pattern Recognition · Computer Science 2019-09-10 Xiaoyu Li , Bo Zhang , Pedro V. Sander , Jing Liao

This paper presents an adaptive convolutional neural network (CNN) architecture that can automate diverse topology optimization (TO) problems having different underlying physics. The architecture uses the encoder-decoder networks with dense…

Computational Engineering, Finance, and Science · Computer Science 2025-09-10 Khaish Singh Chadha , Prabhat Kumar

In this paper we challenge the common assumption that convolutional layers in modern CNNs are translation invariant. We show that CNNs can and will exploit the absolute spatial location by learning filters that respond exclusively to…

Computer Vision and Pattern Recognition · Computer Science 2020-06-02 Osman Semih Kayhan , Jan C. van Gemert

Omnidirectional images and spherical representations of $3D$ shapes cannot be processed with conventional 2D convolutional neural networks (CNNs) as the unwrapping leads to large distortion. Using fast implementations of spherical and…

Computer Vision and Pattern Recognition · Computer Science 2020-12-09 Suhas Lohit , Shubhendu Trivedi

Ideally, 360{\deg} imagery could inherit the deep convolutional neural networks (CNNs) already trained with great success on perspective projection images. However, existing methods to transfer CNNs from perspective to spherical images…

Computer Vision and Pattern Recognition · Computer Science 2019-04-10 Yu-Chuan Su , Kristen Grauman

Equivariant and invariant deep learning models have been developed to exploit intrinsic symmetries in data, demonstrating significant effectiveness in certain scenarios. However, these methods often suffer from limited representation…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Yulu Bai , Jiahong Fu , Qi Xie , Deyu Meng

Deep convolutional neural networks accuracy is heavily impacted by rotations of the input data. In this paper, we propose a convolutional predictor that is invariant to rotations in the input. This architecture is capable of predicting the…

Computer Vision and Pattern Recognition · Computer Science 2021-05-24 Rosemberg Rodriguez Salas , Eva Dokladalova , Petr Dokládal

Invariance under symmetry is an important problem in machine learning. Our paper looks specifically at equivariant neural networks where transformations of inputs yield homomorphic transformations of outputs. Here, steerable CNNs have…

Machine Learning · Computer Science 2021-09-15 Daniel Franzen , Michael Wand

We propose a novel way to measure and understand convolutional neural networks by quantifying the amount of input signal they let in. To do this, an autoencoder (AE) was fine-tuned on gradients from a pre-trained classifier with fixed…

Computer Vision and Pattern Recognition · Computer Science 2018-03-23 Sebastian Palacio , Joachim Folz , Jörn Hees , Federico Raue , Damian Borth , Andreas Dengel

We propose a framework for rotation and translation covariant deep learning using $SE(2)$ group convolutions. The group product of the special Euclidean motion group $SE(2)$ describes how a concatenation of two roto-translations results in…

Computer Vision and Pattern Recognition · Computer Science 2018-06-12 Erik J Bekkers , Maxime W Lafarge , Mitko Veta , Koen AJ Eppenhof , Josien PW Pluim , Remco Duits

Metric learning has received conflicting assessments concerning its suitability for solving instance segmentation tasks. It has been dismissed as theoretically flawed due to the shift equivariance of the employed CNNs and their respective…

Computer Vision and Pattern Recognition · Computer Science 2021-08-20 Josef Lorenz Rumberger , Xiaoyan Yu , Peter Hirsch , Melanie Dohmen , Vanessa Emanuela Guarino , Ashkan Mokarian , Lisa Mais , Jan Funke , Dagmar Kainmueller

In this paper we propose integrating a priori knowledge into both design and training of convolutional neural networks (CNNs) to learn object representations that are invariant to affine transformations (i.e., translation, scale, rotation).…

Computer Vision and Pattern Recognition · Computer Science 2019-09-04 Xenju Xu , Guanghui Wang , Alan Sullivan , Ziming Zhang

Extracting discriminative local features that are invariant to imaging variations is an integral part of establishing correspondences between images. In this work, we introduce a self-supervised learning framework to extract discriminative…

Computer Vision and Pattern Recognition · Computer Science 2023-03-29 Jongmin Lee , Byungjin Kim , Seungwook Kim , Minsu Cho

Convolutional neural networks (CNNs) achieved the state-of-the-art performance in medical image segmentation due to their ability to extract highly complex feature representations. However, it is argued in recent studies that traditional…

Computer Vision and Pattern Recognition · Computer Science 2025-03-31 Zhendi Gong , Andrew P. French , Guoping Qiu , Xin Chen
‹ Prev 1 4 5 6 7 8 10 Next ›