English
Related papers

Related papers: Spatial Transformer Networks

200 papers

Standard convolutional neural networks assume a grid structured input is available and exploit discrete convolutions as their fundamental building blocks. This limits their applicability to many real-world applications. In this paper we…

Computer Vision and Pattern Recognition · Computer Science 2021-01-19 Shenlong Wang , Simon Suo , Wei-Chiu Ma , Andrei Pokrovsky , Raquel Urtasun

Spatial Transformer Networks (STNs) estimate image transformations that can improve downstream tasks by `zooming in' on relevant regions in an image. However, STNs are hard to train and sensitive to mis-predictions of transformations. To…

Machine Learning · Computer Science 2022-06-16 Pola Schwöbel , Frederik Warburg , Martin Jørgensen , Kristoffer H. Madsen , Søren Hauberg

We present an efficient alternative to the convolutional layer using cheap spatial transformations. This construction exploits an inherent spatial redundancy of the learned convolutional filters to enable a much greater parameter…

Computer Vision and Pattern Recognition · Computer Science 2023-08-25 Roy Miles , Krystian Mikolajczyk

Convolutional Neural Networks (CNNs) perform very well in image classification and object detection in recent years, but even the most advanced models have limited rotation invariance. Known solutions include the enhancement of training…

Computer Vision and Pattern Recognition · Computer Science 2022-02-28 Zongbo Hao , Tao Zhang , Mingwang Chen , Kaixu Zhou

Inspired by two basic mechanisms in animal visual systems, we introduce a feature transform technique that imposes invariance properties in the training of deep neural networks. The resulting algorithm requires less parameter tuning, trains…

Computer Vision and Pattern Recognition · Computer Science 2021-12-10 Chengxi Ye , Xiong Zhou , Tristan McKinney , Yanfeng Liu , Qinggang Zhou , Fedor Zhdanov

Systems that perform image manipulation using deep convolutional networks have achieved remarkable realism. Perceptual losses and losses based on adversarial discriminators are the two main classes of learning objectives behind these…

Computer Vision and Pattern Recognition · Computer Science 2018-09-06 Diana Sungatullina , Egor Zakharov , Dmitry Ulyanov , Victor Lempitsky

Transformers demonstrate significant advantages as the building block of modern LLMs. In this work, we study the capacities of Transformers in performing unsupervised learning. We show that multi-layered Transformers, given a sufficiently…

Machine Learning · Statistics 2025-01-14 Yihan He , Yuan Cao , Hong-Yu Chen , Dennis Wu , Jianqing Fan , Han Liu

Exploiting data invariances is crucial for efficient learning in both artificial and biological neural circuits. Understanding how neural networks can discover appropriate representations capable of harnessing the underlying symmetries of…

Disordered Systems and Neural Networks · Physics 2022-10-17 Alessandro Ingrosso , Sebastian Goldt

Determining the different conformational states of a protein and the transition paths between them is key to fully understanding the relationship between biomolecular structure and function. This can be accomplished by sampling protein…

Biological Physics · Physics 2021-03-24 Venkata K. Ramaswamy , Chris G. Willcocks , Matteo T. Degiacomi

When seeing a new object, humans can immediately recognize it across different retinal locations: we say that the internal object representation is invariant to translation. It is commonly believed that Convolutional Neural Networks (CNNs)…

Computer Vision and Pattern Recognition · Computer Science 2020-11-25 Valerio Biscione , Jeffrey Bowers

Data augmentation in feature space is effective to increase data diversity. Previous methods assume that different classes have the same covariance in their feature distributions. Thus, feature transform between different classes is…

Computer Vision and Pattern Recognition · Computer Science 2020-08-05 Yuke Zhu , Yan Bai , Yichen Wei

Convolutional Neural Networks (ConvNets) have shown excellent results on many visual classification tasks. With the exception of ImageNet, these datasets are carefully crafted such that objects are well-aligned at similar scales. Naturally,…

Computer Vision and Pattern Recognition · Computer Science 2014-12-17 Angjoo Kanazawa , Abhishek Sharma , David Jacobs

Vision Transformers (ViTs) have achieved comparable or superior performance than Convolutional Neural Networks (CNNs) in computer vision. This empirical breakthrough is even more remarkable since, in contrast to CNNs, ViTs do not embed any…

Computer Vision and Pattern Recognition · Computer Science 2022-10-18 Samy Jelassi , Michael E. Sander , Yuanzhi Li

Models of neural networks have proven their utility in the development of learning algorithms in computer science and in the theoretical study of brain dynamics in computational neuroscience. We propose in this paper a spatial neural…

Neural and Evolutionary Computing · Computer Science 2014-05-06 Lucas Antiqueira , Liang Zhao

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

Curriculum learning is a bio-inspired training technique that is widely adopted to machine learning for improved optimization and better training of neural networks regarding the convergence rate or obtained accuracy. The main concept in…

Computer Vision and Pattern Recognition · Computer Science 2021-08-24 Fatemeh Azimi , Jean-Francois Jacques Nicolas Nies , Sebastian Palacio , Federico Raue , Jörn Hees , Andreas Dengel

The transformer is a neural network component that can be used to learn useful representations of sequences or sets of data-points. The transformer has driven recent advances in natural language processing, computer vision, and…

Machine Learning · Computer Science 2026-01-21 Richard E. Turner

Convolutional Neural Networks need the construction of informative features, which are determined by channel-wise and spatial-wise information at the network's layers. In this research, we focus on bringing in a novel solution that uses…

Computer Vision and Pattern Recognition · Computer Science 2022-04-01 Jerrin Bright , Suryaprakash Rajkumar , Arockia Selvakumar Arockia Doss

Convolutional Neural Networks (CNN) offer state of the art performance in various computer vision tasks. Many of those tasks require different subtypes of affine invariances (scale, rotational, translational) to image transformations.…

Computer Vision and Pattern Recognition · Computer Science 2023-10-13 Facundo Manuel Quiroga , Franco Ronchetti , Laura Lanzarini , Aurelio Fernandez-Bariviera

Transformers have demonstrated remarkable success across various applications. However, the success of transformers have not been understood in theory. In this work, we give a case study of how transformers can be trained to learn a classic…

Machine Learning · Statistics 2025-04-14 Chenyang Zhang , Xuran Meng , Yuan Cao