English
Related papers

Related papers: From CNNs to Shift-Invariant Twin Models Based on …

200 papers

It is well known that Convolutional Neural Networks (CNNs) have significant redundancy in their filter weights. Various methods have been proposed in the literature to compress trained CNNs. These include techniques like pruning weights,…

Machine Learning · Computer Science 2019-06-12 Muhammad Tayyab , Abhijit Mahalanobis

In the last ten years, Convolutional Neural Networks (CNNs) have formed the basis of deep-learning architectures for most computer vision tasks. However, they are not necessarily optimal. For example, mathematical morphology is known to be…

Computer Vision and Pattern Recognition · Computer Science 2022-03-24 Theodore Aouad , Hugues Talbot

Building large models with parameter sharing accounts for most of the success of deep convolutional neural networks (CNNs). In this paper, we propose doubly convolutional neural networks (DCNNs), which significantly improve the performance…

Machine Learning · Computer Science 2016-11-01 Shuangfei Zhai , Yu Cheng , Weining Lu , Zhongfei Zhang

Convolutional Neural Networks (CNN) have been successful in processing data signals that are uniformly sampled in the spatial domain (e.g., images). However, most data signals do not natively exist on a grid, and in the process of being…

Computer Vision and Pattern Recognition · Computer Science 2019-01-09 Chiyu "Max" Jiang , Dequan Wang , Jingwei Huang , Philip Marcus , Matthias Nießner

Multispectral image pairs can provide the combined information, making object detection applications more reliable and robust in the open world. To fully exploit the different modalities, we present a simple yet effective cross-modality…

Image and Video Processing · Electrical Eng. & Systems 2022-10-05 Fang Qingyun , Han Dapeng , Wang Zhaokui

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

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

Most modern convolutional neural networks (CNNs) used for object recognition are built using the same principles: Alternating convolution and max-pooling layers followed by a small number of fully connected layers. We re-evaluate the state…

Machine Learning · Computer Science 2015-04-14 Jost Tobias Springenberg , Alexey Dosovitskiy , Thomas Brox , Martin Riedmiller

In this paper, we present Shift Convolution Network (ShiftConvNet) to provide matching capability between two feature maps for stereo estimation. The proposed method can speedily produce a highly accurate disparity map from stereo images. A…

Computer Vision and Pattern Recognition · Computer Science 2019-11-21 Jian Xie

Convolutional Neural Networks (CNN) have been used in Automatic Speech Recognition (ASR) to learn representations directly from the raw signal instead of hand-crafted acoustic features, providing a richer and lossless input signal. Recent…

Sound · Computer Science 2020-02-12 Paul-Gauthier Noé , Titouan Parcollet , Mohamed Morchid

Single image deraining is a crucial problem because rain severely degenerates the visibility of images and affects the performance of computer vision tasks like outdoor surveillance systems and intelligent vehicles. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2021-10-11 Hao-Hsiang Yang , Chao-Han Huck Yang , Yu-Chiang Frank Wang

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

In this work, we investigate the value of employing deep learning for the task of wireless signal modulation recognition. Recently in [1], a framework has been introduced by generating a dataset using GNU radio that mimics the imperfections…

Machine Learning · Computer Science 2018-01-08 Xiaoyu Liu , Diyu Yang , Aly El Gamal

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

In the context of skeleton-based action recognition, graph convolutional networks (GCNs) have been rapidly developed, whereas convolutional neural networks (CNNs) have received less attention. One reason is that CNNs are considered poor in…

Computer Vision and Pattern Recognition · Computer Science 2021-12-10 Kailin Xu , Fanfan Ye , Qiaoyong Zhong , Di Xie

Transition prediction is an important aspect of aerodynamic design because of its impact on skin friction and potential coupling with flow separation characteristics. Traditionally, the modeling of transition has relied on correlation-based…

In this paper we introduce ShiftCNN, a generalized low-precision architecture for inference of multiplierless convolutional neural networks (CNNs). ShiftCNN is based on a power-of-two weight representation and, as a result, performs only…

Computer Vision and Pattern Recognition · Computer Science 2017-06-09 Denis A. Gudovskiy , Luca Rigazio

Convolutional neural networks (CNNs) are inherently limited to model geometric transformations due to the fixed geometric structures in its building modules. In this work, we introduce two new modules to enhance the transformation modeling…

Computer Vision and Pattern Recognition · Computer Science 2017-06-06 Jifeng Dai , Haozhi Qi , Yuwen Xiong , Yi Li , Guodong Zhang , Han Hu , Yichen Wei

Despite recent advances in multi-scale deep representations, their limitations are attributed to expensive parameters and weak fusion modules. Hence, we propose an efficient approach to fuse multi-scale deep representations, called…

Computer Vision and Pattern Recognition · Computer Science 2016-11-18 Yu Liu , Yanming Guo , Michael S. Lew

Convolutional neural networks (CNNs) and transformer architectures offer strengths for modeling temporal data: CNNs excel at capturing local patterns and translational invariances, while transformers effectively model long-range…

Machine Learning · Computer Science 2025-10-09 Stefano F. Stefenon , João P. Matos-Carvalho , Valderi R. Q. Leithardt , Kin-Choong Yow