Convolutional Neural Networks With Gated Recurrent Connections

Computer Science > Computer Vision and Pattern Recognition arXiv:2106.02859 (cs) [Submitted on 5 Jun 2021] Title:Convolutional Neural Networks with Gated Recurrent Connections Authors:Jianfeng Wang, Xiaolin Hu View a PDF of the paper titled Convolutional Neural Networks with Gated Recurrent Connections, by Jianfeng Wang and 1 other authors View PDF

Abstract:The convolutional neural network (CNN) has become a basic model for solving many computer vision problems. In recent years, a new class of CNNs, recurrent convolution neural network (RCNN), inspired by abundant recurrent connections in the visual systems of animals, was proposed. The critical element of RCNN is the recurrent convolutional layer (RCL), which incorporates recurrent connections between neurons in the standard convolutional layer. With increasing number of recurrent computations, the receptive fields (RFs) of neurons in RCL expand unboundedly, which is inconsistent with biological facts. We propose to modulate the RFs of neurons by introducing gates to the recurrent connections. The gates control the amount of context information inputting to the neurons and the neurons' RFs therefore become adaptive. The resulting layer is called gated recurrent convolution layer (GRCL). Multiple GRCLs constitute a deep model called gated RCNN (GRCNN). The GRCNN was evaluated on several computer vision tasks including object recognition, scene text recognition and object detection, and obtained much better results than the RCNN. In addition, when combined with other adaptive RF techniques, the GRCNN demonstrated competitive performance to the state-of-the-art models on benchmark datasets for these tasks. The codes are released at \href{this https URL}{this https URL}.

Comments:	Accepted by TPAMI. An extension of our previous NeurIPS 2017 paper "Gated recurrent convolution neural network for OCR". We demonstrate the good performance of GRCNN on image classification and object detection. Codes are available at: this https URL
Subjects:	Computer Vision and Pattern Recognition (cs.CV)
Cite as:	arXiv:2106.02859 [cs.CV]
(or arXiv:2106.02859v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2106.02859 Focus to learn more arXiv-issued DOI via DataCite
Related DOI:	https://doi.org/10.1109/TPAMI.2021.3054614 Focus to learn more DOI(s) linking to related resources

Submission history

From: Jianfeng Wang [view email] [v1] Sat, 5 Jun 2021 10:14:59 UTC (2,577 KB) Full-text links:

Access Paper:

View a PDF of the paper titled Convolutional Neural Networks with Gated Recurrent Connections, by Jianfeng Wang and 1 other authors
• View PDF
• TeX Source

view license Current browse context: cs.CV < prev | next > new | recent | 2021-06 Change to browse by: cs

References & Citations

• NASA ADS
• Google Scholar
• Semantic Scholar

DBLP - CS Bibliography

listing | bibtex Jianfeng WangXiaolin Hu export BibTeX citation

BibTeX formatted citation

× loading... Data provided by:

Bookmark

Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) Links to Code Toggle Papers with Code (What is Papers with Code?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?)

• Author
• Venue
• Institution
• Topic

About arXivLabs arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)