Recent Advances in Convolutional Neural Networks
Jiuxiang Gu, Zhenhua Wang, Jason Kuen, Lianyang Ma, Amir Shahroudy, Bing Shuai, Ting Liu, Xingxing Wang, Gang Wang
(Submitted on 22 Dec 2015 (v1), last revised 5 Jan 2017 (this version, v5))
In the last few years, deep learning has led to very good performance on a variety of problems, such as visual recognition, speech recognition and natural language processing. Among different types of deep neural networks, convolutional neural networks have been most extensively studied. Due to the lack of training data and computing power in early days, it is hard to train a large high-capacity convolutional neural network without overfitting. After the rapid growth in the amount of the annotated data and the recent improvements in the strengths of graphics processor units (GPUs), the research on convolutional neural networks has been emerged swiftly and achieved state-of-the-art results on various tasks. In this paper, we provide a broad survey of the recent advances in convolutional neural networks. Besides, we also introduce some applications of convolutional neural networks in computer vision.
Comments: review, journal
Subjects: Computer Vision and Pattern Recognition (cs.CV); Learning (cs.LG); Neural and Evolutionary Computing (cs.NE)
Cite as: arXiv:1512.07108 [cs.CV]
(or arXiv:1512.07108v5 [cs.CV] for this version)
Submission history
From: Jiuxiang Gu Mr [view email]
[v1] Tue, 22 Dec 2015 14:54:34 GMT (1693kb,D)
[v2] Tue, 5 Jul 2016 11:39:16 GMT (578kb,D)
[v3] Mon, 1 Aug 2016 01:54:59 GMT (439kb,D)
[v4] Sat, 6 Aug 2016 12:38:35 GMT (438kb,D)
[v5] Thu, 5 Jan 2017 05:45:53 GMT (3100kb,D)
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)