English
Related papers

Related papers: Global Second-order Pooling Convolutional Networks

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

Compared with global average pooling in existing deep convolutional neural networks (CNNs), global covariance pooling can capture richer statistics of deep features, having potential for improving representation and generalization abilities…

Computer Vision and Pattern Recognition · Computer Science 2020-08-12 Qilong Wang , Jiangtao Xie , Wangmeng Zuo , Lei Zhang , Peihua Li

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

Graph Neural Networks (GNNs), which generalize deep neural networks to graph-structured data, have drawn considerable attention and achieved state-of-the-art performance in numerous graph related tasks. However, existing GNN models mainly…

Machine Learning · Computer Science 2019-12-30 Zhen Zhang , Jiajun Bu , Martin Ester , Jianfeng Zhang , Chengwei Yao , Zhi Yu , Can Wang

Global covariance pooling in convolutional neural networks has achieved impressive improvement over the classical first-order pooling. Recent works have shown matrix square root normalization plays a central role in achieving…

Computer Vision and Pattern Recognition · Computer Science 2018-04-03 Peihua Li , Jiangtao Xie , Qilong Wang , Zilin Gao

Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, improve on the previous best result in semantic segmentation. Our…

Computer Vision and Pattern Recognition · Computer Science 2016-05-23 Evan Shelhamer , Jonathan Long , Trevor Darrell

Convolutional Neural Networks (CNNs) have been successfully applied to many computer vision tasks, such as image classification. By performing linear combinations and element-wise nonlinear operations, these networks can be thought of as…

Computer Vision and Pattern Recognition · Computer Science 2017-03-21 Kaicheng Yu , Mathieu Salzmann

Deep networks have been successfully applied to visual tracking by learning a generic representation offline from numerous training images. However the offline training is time-consuming and the learned generic representation may be less…

Computer Vision and Pattern Recognition · Computer Science 2015-08-25 Kaihua Zhang , Qingshan Liu , Yi Wu , Ming-Hsuan Yang

Deep convolutional neural networks have been successfully applied to image classification tasks. When these same networks have been applied to image retrieval, the assumption has been made that the last layers would give the best…

Computer Vision and Pattern Recognition · Computer Science 2015-05-01 Joe Yue-Hei Ng , Fan Yang , Larry S. Davis

Deep convolutional neural networks (ConvNets) of 3-dimensional kernels allow joint modeling of spatiotemporal features. These networks have improved performance of video and volumetric image analysis, but have been limited in size due to…

Computer Vision and Pattern Recognition · Computer Science 2017-06-13 David Budden , Alexander Matveev , Shibani Santurkar , Shraman Ray Chaudhuri , Nir Shavit

Bilinear pooling of Convolutional Neural Network (CNN) features [22, 23], and their compact variants [10], have been shown to be effective at fine-grained recognition, scene categorization, texture recognition, and visual question-answering…

Computer Vision and Pattern Recognition · Computer Science 2017-07-24 Tsung-Yu Lin , Subhransu Maji

Downsampling is widely adopted to achieve a good trade-off between accuracy and latency for visual recognition. Unfortunately, the commonly used pooling layers are not learned, and thus cannot preserve important information. As another…

Computer Vision and Pattern Recognition · Computer Science 2022-07-26 Ho Man Kwan , Shenghui Song

Depth is one of the keys that make neural networks succeed in the task of large-scale image recognition. The state-of-the-art network architectures usually increase the depths by cascading convolutional layers or building blocks. In this…

Computer Vision and Pattern Recognition · Computer Science 2018-02-13 Siyuan Qiao , Zhishuai Zhang , Wei Shen , Bo Wang , Alan Yuille

Following the success of deep convolutional networks in various vision and speech related tasks, researchers have started investigating generalizations of the well-known technique for graph-structured data. A recently-proposed method called…

Social and Information Networks · Computer Science 2018-09-21 John Boaz Lee , Ryan A. Rossi , Xiangnan Kong , Sungchul Kim , Eunyee Koh , Anup Rao

Graph convolutional networks (GCNs) have been successfully applied in node classification tasks of network mining. However, most of these models based on neighborhood aggregation are usually shallow and lack the "graph pooling" mechanism,…

Social and Information Networks · Computer Science 2019-06-11 Fenyu Hu , Yanqiao Zhu , Shu Wu , Liang Wang , Tieniu Tan

Graph convolutional neural networks (GCNNs) are a powerful extension of deep learning techniques to graph-structured data problems. We empirically evaluate several pooling methods for GCNNs, and combinations of those graph pooling methods…

Signal Processing · Electrical Eng. & Systems 2020-04-08 Mark Cheung , John Shi , Lavender Yao Jiang , Oren Wright , José M. F. Moura

Deep neural networks with alternating convolutional, max-pooling and decimation layers are widely used in state of the art architectures for computer vision. Max-pooling purposefully discards precise spatial information in order to create…

Computer Vision and Pattern Recognition · Computer Science 2016-04-19 Sina Honari , Jason Yosinski , Pascal Vincent , Christopher Pal

In synthetic aperture radar (SAR) image change detection, it is quite challenging to exploit the changing information from the noisy difference image subject to the speckle. In this paper, we propose a multi-scale spatial pooling (MSSP)…

Computer Vision and Pattern Recognition · Computer Science 2020-05-25 Jia-Wei Chen , Rongfang Wang , Fan Ding , Bo Liu , Licheng Jiao , Jie Zhang

Feature pooling layers (e.g., max pooling) in convolutional neural networks (CNNs) serve the dual purpose of providing increasingly abstract representations as well as yielding computational savings in subsequent convolutional layers. We…

Machine Learning · Computer Science 2016-11-17 Shuangfei Zhai , Hui Wu , Abhishek Kumar , Yu Cheng , Yongxi Lu , Zhongfei Zhang , Rogerio Feris

The inception network has been shown to provide good performance on image classification problems, but there are not much evidences that it is also effective for the image restoration or pixel-wise labeling problems. For image restoration…

Computer Vision and Pattern Recognition · Computer Science 2017-01-24 Yoonsik Kim , Insung Hwang , Nam Ik Cho