English
Related papers

Related papers: TI-POOLING: transformation-invariant pooling for f…

200 papers

Learning invariant representations is an important problem in machine learning and pattern recognition. In this paper, we present a novel framework of transformation-invariant feature learning by incorporating linear transformations into…

Machine Learning · Computer Science 2012-07-03 Kihyuk Sohn , Honglak Lee

In most convolution neural networks (CNNs), downsampling hidden layers is adopted for increasing computation efficiency and the receptive field size. Such operation is commonly so-called pooling. Maximation and averaging over sliding…

Computer Vision and Pattern Recognition · Computer Science 2020-10-12 Hao Zhang , Jianwei Ma

Recent advances in image clustering typically focus on learning better deep representations. In contrast, we present an orthogonal approach that does not rely on abstract features but instead learns to predict image transformations and…

Computer Vision and Pattern Recognition · Computer Science 2020-10-29 Tom Monnier , Thibault Groueix , Mathieu Aubry

The process of pooling vertices involves the creation of a new vertex, which becomes adjacent to all the vertices that were originally adjacent to the endpoints of the vertices being pooled. After this, the endpoints of these vertices and…

Machine Learning · Computer Science 2025-09-23 Shanookha Ali , Nitha Niralda , Sunil Mathew

In this contribution, we show how to incorporate prior knowledge to a deep neural network architecture in a principled manner. We enforce feature space invariances using a novel layer based on invariant integration. This allows us to…

Machine Learning · Computer Science 2020-04-21 Matthias Rath , Alexandru Paul Condurache

Encouraged by the success of Convolutional Neural Networks (CNNs) in image classification, recently much effort is spent on applying CNNs to video based action recognition problems. One challenge is that video contains a varying number of…

Computer Vision and Pattern Recognition · Computer Science 2015-04-17 Peng Wang , Yuanzhouhan Cao , Chunhua Shen , Lingqiao Liu , Heng Tao Shen

A number of recent studies have shown that a Deep Convolutional Neural Network (DCNN) pretrained on a large dataset can be adopted as a universal image description which leads to astounding performance in many visual classification tasks.…

Computer Vision and Pattern Recognition · Computer Science 2014-12-01 Lingqiao Liu , Chunhua Shen , Anton van den Hengel

Pooling layers are essential building blocks of convolutional neural networks (CNNs), to reduce computational overhead and increase the receptive fields of proceeding convolutional operations. Their goal is to produce downsampled volumes…

Computer Vision and Pattern Recognition · Computer Science 2022-12-05 Alexandros Stergiou , Ronald Poppe

Thanks to the use of convolution and pooling layers, convolutional neural networks were for a long time thought to be shift-invariant. However, recent works have shown that the output of a CNN can change significantly with small shifts in…

Computer Vision and Pattern Recognition · Computer Science 2021-04-01 Anadi Chaman , Ivan Dokmanić

Pooling operations, which can be calculated at low cost and serve as a linear or nonlinear transfer function for data reduction, are found in almost every modern neural network. Countless modern approaches have already tackled replacing the…

Computer Vision and Pattern Recognition · Computer Science 2021-01-19 Wolfgang Fuhl , Enkelejda Kasneci

Learning transformation invariant representations of visual data is an important problem in computer vision. Deep convolutional networks have demonstrated remarkable results for image and video classification tasks. However, they have…

Computer Vision and Pattern Recognition · Computer Science 2017-03-02 Renata Khasanova , Pascal Frossard

Convolutional Neural Networks (CNNs) use pooling to decrease the size of activation maps. This process is crucial to increase the receptive fields and to reduce computational requirements of subsequent convolutions. An important feature of…

Computer Vision and Pattern Recognition · Computer Science 2021-03-19 Alexandros Stergiou , Ronald Poppe , Grigorios Kalliatakis

This paper presents a novel approach to exploit the distinctive invariant features in convolutional neural network. The proposed CNN model uses Scale Invariant Feature Transform (SIFT) descriptor instead of the max-pooling layer.…

Computer Vision and Pattern Recognition · Computer Science 2019-04-02 Abhay Kumar , Nishant Jain , Chirag Singh , Suraj Tripathi

Convolutional neural networks (CNNs) have been established as the main workhorse in image data processing; nonetheless, they require large amounts of data to train, often produce overconfident predictions, and frequently lack the ability to…

Computer Vision and Pattern Recognition · Computer Science 2025-10-14 Sarah Harkins Dayton , Hayden Everett , Ioannis Schizas , David L. Boothe , Vasileios Maroulas

Deep convolutional neural networks have recently proven extremely competitive in challenging image recognition tasks. This paper proposes the epitomic convolution as a new building block for deep neural networks. An epitomic convolution…

Computer Vision and Pattern Recognition · Computer Science 2014-06-12 George Papandreou

Standard Convolutional Neural Networks (CNNs) designed for computer vision tasks tend to have large intermediate activation maps. These require large working memory and are thus unsuitable for deployment on resource-constrained devices…

Computer Vision and Pattern Recognition · Computer Science 2020-10-26 Oindrila Saha , Aditya Kusupati , Harsha Vardhan Simhadri , Manik Varma , Prateek Jain

The pooling operation is a cornerstone element of convolutional neural networks. These elements generate receptive fields for neurons, in which local perturbations should have minimal effect on the output activations, increasing robustness…

Computer Vision and Pattern Recognition · Computer Science 2020-11-10 Dóra Babicz , Soma Kontár , Márk Pető , András Fülöp , Gergely Szabó , András Horváth

We reduce training time in convolutional networks (CNNs) with a method that, for some of the mini-batches: a) scales down the resolution of input images via downsampling, and b) reduces the forward pass operations via pooling on the…

Machine Learning · Computer Science 2019-10-16 Zissis Poulos , Ali Nouri , Andreas Moshovos

In this Letter we supervisedly train neural networks to distinguish different topological phases in the context of topological band insulators. After training with Hamiltonians of one-dimensional insulators with chiral symmetry, the neural…

Mesoscale and Nanoscale Physics · Physics 2018-05-31 Pengfei Zhang , Huitao Shen , Hui Zhai

The concept of sparsity has been extensively applied for regularization in image reconstruction. Typically, sparsifying transforms are either pre-trained on ground-truth images or adaptively trained during the reconstruction. Thereby,…

Image and Video Processing · Electrical Eng. & Systems 2022-03-07 Andreas Kofler , Christian Wald , Tobias Schaeffter , Markus Haltmeier , Christoph Kolbitsch