English
Related papers

Related papers: Improving Shift Invariance in Convolutional Neural…

200 papers

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

We propose learnable polyphase sampling (LPS), a pair of learnable down/upsampling layers that enable truly shift-invariant and equivariant convolutional networks. LPS can be trained end-to-end from data and generalizes existing handcrafted…

Computer Vision and Pattern Recognition · Computer Science 2022-10-17 Renan A. Rojas-Gomez , Teck-Yian Lim , Alexander G. Schwing , Minh N. Do , Raymond A. Yeh

Convolutional neural networks have shown remarkable performance in recent years on various computer vision problems. However, the traditional convolutional neural network architecture lacks a critical property: shift equivariance and…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Quentin Gabot , Teck-Yian Lim , Jérémy Fix , Joana Frontera-Pons , Chengfang Ren , Jean-Philippe Ovarlez

Radio spectrum monitoring in contested environments motivates the need for reliable automatic signal classification technology. Prior work highlights deep learning as a promising approach, but existing models depend on brute-force Doppler…

Signal Processing · Electrical Eng. & Systems 2025-11-19 Avi Bagchi , Dwight Hutchenson

A fundamental problem in object recognition is the development of image representations that are invariant to common transformations such as translation, rotation, and small deformations. There are multiple hypotheses regarding the source…

Computer Vision and Pattern Recognition · Computer Science 2018-01-08 Eric Kauderer-Abrams

This paper focuses on improving the mathematical interpretability of convolutional neural networks (CNNs) in the context of image classification. Specifically, we tackle the instability issue arising in their first layer, which tends to…

Computer Vision and Pattern Recognition · Computer Science 2025-04-21 Hubert Leterme , Kévin Polisano , Valérie Perrier , Karteek Alahari

We address the problem that state-of-the-art Convolution Neural Networks (CNN) classifiers are not invariant to small shifts. The problem can be solved by the removal of sub-sampling operations such as stride and max pooling, but at a cost…

Computer Vision and Pattern Recognition · Computer Science 2019-11-27 Ganesh Sundaramoorthi , Timothy E. Wang

Recent studies have put into question the commonly assumed shift invariance property of convolutional networks, showing that small shifts in the input can affect the output predictions substantially. In this paper, we analyze the benefits…

Sound · Computer Science 2021-07-23 Eduardo Fonseca , Andres Ferraro , Xavier Serra

Convolutional neural networks lack shift equivariance due to the presence of downsampling layers. In image classification, adaptive polyphase downsampling (APS-D) was recently proposed to make CNNs perfectly shift invariant. However, in…

Computer Vision and Pattern Recognition · Computer Science 2021-12-08 Anadi Chaman , Ivan Dokmanić

Convolutional Neural Networks (CNNs) have demonstrated state-of-the-art performance on many visual recognition tasks. However, the combination of convolution and pooling operations only shows invariance to small local location changes in…

Computer Vision and Pattern Recognition · Computer Science 2019-12-02 Xu Shen , Xinmei Tian , Shaoyan Sun , Dacheng Tao

Convolutional neural networks (CNNs) with convolutional and pooling operations along the frequency axis have been proposed to attain invariance to frequency shifts of features. However, this is inappropriate with regard to the fact that…

Computation and Language · Computer Science 2016-08-24 Hwaran Lee , Geonmin Kim , Ho-Gyeong Kim , Sang-Hoon Oh , Soo-Young Lee

Modern convolutional networks are not shift-invariant, as small input shifts or translations can cause drastic changes in the output. Commonly used downsampling methods, such as max-pooling, strided-convolution, and average-pooling, ignore…

Computer Vision and Pattern Recognition · Computer Science 2019-06-11 Richard Zhang

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

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

The convolutional neural networks (CNNs) are not inherently shift invariant or equivariant. The downsampling operation, used in CNNs, is one of the key reasons which breaks the shift invariant property of a CNN. Conversely, downsampling…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Jaspreet Singh , Petra Bosilj , Grzegorz Cielniak

In industrial defect segmentation tasks, while pixel accuracy and Intersection over Union (IoU) are commonly employed metrics to assess segmentation performance, the output consistency (also referred to equivalence) of the model is often…

Computer Vision and Pattern Recognition · Computer Science 2023-10-02 Zhen Qu , Xian Tao , Fei Shen , Zhengtao Zhang , Tao Li

Deep convolutional neural networks (CNN) have shown their promise as a universal representation for recognition. However, global CNN activations lack geometric invariance, which limits their robustness for classification and matching of…

Computer Vision and Pattern Recognition · Computer Science 2014-09-10 Yunchao Gong , Liwei Wang , Ruiqi Guo , Svetlana Lazebnik

In this paper we present a deep neural network topology that incorporates a simple to implement transformation invariant pooling operator (TI-POOLING). This operator is able to efficiently handle prior knowledge on nuisance variations in…

Computer Vision and Pattern Recognition · Computer Science 2016-09-23 Dmitry Laptev , Nikolay Savinov , Joachim M. Buhmann , Marc Pollefeys

Deep learning time-series processing often relies on convolutional neural networks with overlapping windows. This overlap allows the network to produce an output faster than the window length. However, it introduces additional computations.…

Machine Learning · Computer Science 2024-08-07 Christodoulos Kechris , Jonathan Dan , Jose Miranda , David Atienza

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
‹ Prev 1 2 3 10 Next ›