English
Related papers

Related papers: Recombinator Networks: Learning Coarse-to-Fine Fea…

200 papers

Most convolutional neural networks use some method for gradually downscaling the size of the hidden layers. This is commonly referred to as pooling, and is applied to reduce the number of parameters, improve invariance to certain…

Computer Vision and Pattern Recognition · Computer Science 2018-04-13 Faraz Saeedan , Nicolas Weber , Michael Goesele , Stefan Roth

Infrared and visible image fusion aims to generate synthetic images simultaneously containing salient features and rich texture details, which can be used to boost downstream tasks. However, existing fusion methods are suffering from the…

Computer Vision and Pattern Recognition · Computer Science 2023-07-06 Hui Li , Yongbiao Xiao , Chunyang Cheng , Zhongwei Shen , Xiaoning Song

To parse images into fine-grained semantic parts, the complex fine-grained elements will put it in trouble when using off-the-shelf semantic segmentation networks. In this paper, for image parsing task, we propose to parse images from…

Computer Vision and Pattern Recognition · Computer Science 2018-04-24 Jiagao Hu , Zhengxing Sun , Yunhan Sun , Jinlong Shi

Object co-segmentation is to segment the shared objects in multiple relevant images, which has numerous applications in computer vision. This paper presents a spatial and semantic modulated deep network framework for object co-segmentation.…

Computer Vision and Pattern Recognition · Computer Science 2019-12-02 Kaihua Zhang , Jin Chen , Bo Liu , Qingshan Liu

Recently, very deep convolutional neural networks (CNNs) have shown outstanding performance in object recognition and have also been the first choice for dense classification problems such as semantic segmentation. However, repeated…

Computer Vision and Pattern Recognition · Computer Science 2016-11-28 Guosheng Lin , Anton Milan , Chunhua Shen , Ian Reid

Pooling layers (e.g., max and average) may overlook important information encoded in the spatial arrangement of pixel intensity and/or feature values. We propose a novel lacunarity pooling layer that aims to capture the spatial…

Computer Vision and Pattern Recognition · Computer Science 2024-07-09 Akshatha Mohan , Joshua Peeples

Most existing methods usually formulate the non-blind deconvolution problem into a maximum-a-posteriori framework and address it by manually designing kinds of regularization terms and data terms of the latent clear images. However,…

Computer Vision and Pattern Recognition · Computer Science 2022-07-21 Pin-Hung Kuo , Jinshan Pan , Shao-Yi Chien , Ming-Hsuan Yang

Bilinear pooling has been recently proposed as a feature encoding layer, which can be used after the convolutional layers of a deep network, to improve performance in multiple vision tasks. Different from conventional global average pooling…

Computer Vision and Pattern Recognition · Computer Science 2018-04-02 Mengran Gou , Fei Xiong , Octavia Camps , Mario Sznaier

Deep Convolutional Neural Networks (DCNNs) commonly use generic `max-pooling' (MP) layers to extract deformation-invariant features, but we argue in favor of a more refined treatment. First, we introduce epitomic convolution as a building…

Computer Vision and Pattern Recognition · Computer Science 2014-12-02 George Papandreou , Iasonas Kokkinos , Pierre-André Savalle

Several recent approaches showed how the representations learned by Convolutional Neural Networks can be repurposed for novel tasks. Most commonly it has been shown that the activation features of the last fully connected layers (fc7 or…

Computer Vision and Pattern Recognition · Computer Science 2015-09-22 Arsalan Mousavian , Jana Kosecka

Recent advances in deep learning have shown exciting promise in filling large holes and lead to another orientation for image inpainting. However, existing learning-based methods often create artifacts and fallacious textures because of…

Computer Vision and Pattern Recognition · Computer Science 2018-12-05 Qingguo Xiao , Guangyao Li , Qiaochuan Chen

There are a variety of approaches to obtain a vast receptive field with convolutional neural networks (CNNs), such as pooling or striding convolutions. Most of these approaches were initially designed for image classification and later…

Computer Vision and Pattern Recognition · Computer Science 2020-06-16 Omid Hosseini Jafari , Carsten Rother

We consider the problem of semantic image segmentation using deep convolutional neural networks. We propose a novel network architecture called the label refinement network that predicts segmentation labels in a coarse-to-fine fashion at…

Computer Vision and Pattern Recognition · Computer Science 2017-03-03 Md Amirul Islam , Shujon Naha , Mrigank Rochan , Neil Bruce , Yang Wang

Convolutional rectifier networks, i.e. convolutional neural networks with rectified linear activation and max or average pooling, are the cornerstone of modern deep learning. However, despite their wide use and success, our theoretical…

Neural and Evolutionary Computing · Computer Science 2016-10-18 Nadav Cohen , Amnon Shashua

A deep generative model is developed for representation and analysis of images, based on a hierarchical convolutional dictionary-learning framework. Stochastic {\em unpooling} is employed to link consecutive layers in the model, yielding…

Computer Vision and Pattern Recognition · Computer Science 2015-12-25 Yunchen Pu , Xin Yuan , Andrew Stevens , Chunyuan Li , Lawrence Carin

As aliasing artefacts are highly structural and non-local, many MRI reconstruction networks use pooling to enlarge filter coverage and incorporate global context. However, this inadvertently impedes fine detail recovery as downsampling…

Image and Video Processing · Electrical Eng. & Systems 2023-12-01 Wendi Ma , Marlon Bran Lorenzana , Wei Dai , Hongfu Sun , Shekhar S. Chandra

Downsampling layers, including pooling and strided convolutions, are crucial components of the convolutional neural network architecture that determine both the granularity/scale of image feature analysis as well as the receptive field size…

Computer Vision and Pattern Recognition · Computer Science 2023-06-22 Mehraveh Javan , Matthew Toews , Marco Pedersoli

Scene parsing from images is a fundamental yet challenging problem in visual content understanding. In this dense prediction task, the parsing model assigns every pixel to a categorical label, which requires the contextual information of…

Computer Vision and Pattern Recognition · Computer Science 2020-11-06 Litao Yu , Yongsheng Gao , Jun Zhou , Jian Zhang , Qiang Wu

In this work, we revisit the global average pooling layer proposed in [13], and shed light on how it explicitly enables the convolutional neural network to have remarkable localization ability despite being trained on image-level labels.…

Computer Vision and Pattern Recognition · Computer Science 2015-12-15 Bolei Zhou , Aditya Khosla , Agata Lapedriza , Aude Oliva , Antonio Torralba

We seek to improve deep neural networks by generalizing the pooling operations that play a central role in current architectures. We pursue a careful exploration of approaches to allow pooling to learn and to adapt to complex and variable…

Machine Learning · Statistics 2015-10-13 Chen-Yu Lee , Patrick W. Gallagher , Zhuowen Tu