Mask-CNN: Localizing parts and selecting descriptors for fine-grained bird species categorization

in news •  7 years ago 

By a News Reporter-Staff News Editor at Journal of Robotics & Machine Learning -- Research findings on Pattern Analysis are discussed in a new report. According to news reporting out of Jiangsu, People’s Republic of China, by VerticalNews editors, research stated, “Fine-grained image recognition is a challenging computer vision problem, due to the small inter-class variations caused by highly similar subordinate categories, and the large intra-class variations in poses, scales and rotations. In this paper, we prove that selecting useful deep descriptors contributes well to fine-grained image recognition.”

Financial support for this research came from National Natural Science Foundation of China.

Our news journalists obtained a quote from the research from Nanjing University, “Specifically, a novel Mask-CNN model without the fully connected layers is proposed. Based on the part annotations, the proposed model consists of a fully convolutional network to both locate the discriminative parts (e.g., head and torso), and more importantly generate weighted object/part masks for selecting useful and meaningful convolutional descriptors. After that, a three-stream Mask-CNN model is built for aggregating the selected object- and part-level descriptors simultaneously. Thanks to discarding the parameter redundant fully connected layers, our Mask-CNN has a small feature dimensionality and efficient inference speed by comparing with other fine-grained approaches.”

According to the news editors, the research concluded: “Furthermore, we obtain a new state-of-the-art accuracy on two challenging fine-grained bird species categorization datasets, which validates the effectiveness of both the descriptor selection scheme and the proposed Mask-CNN model.”

For more information on this research see: Mask-CNN: Localizing parts and selecting descriptors for fine-grained bird species categorization. Pattern Recognition , 2018;76():704-714. Pattern Recognition can be contacted at: Elsevier Sci Ltd, The Boulevard, Langford Lane, Kidlington, Oxford OX5 1GB, Oxon, England. (Elsevier - www.elsevier.com; Pattern Recognition - http://www.journals.elsevier.com/pattern-recognition/)

Our news journalists report that additional information may be obtained by contacting J.X. Wu, Nanjing University, Natl Key Lab Novel Software Technol, Nanjing, Jiangsu, People’s Republic of China. Additional authors for this research include C.W. Xie, X.S. Wei and C.H. Shen.

The direct object identifier (DOI) for that additional information is: https://doi.org/10.1016/j.patcog.2017.10.002. This DOI is a link to an online electronic document that is either free or for purchase, and can be your direct source for a journal article and its citation.

Our reports deliver fact-based news of research and discoveries from around the world. Copyright 2018, NewsRx LLC

CITATION: (2018-03-12), Findings in the Area of Pattern Analysis Reported from Nanjing University (Mask-CNN: Localizing parts and selecting descriptors for fine-grained bird species categorization), Journal of Robotics & Machine Learning, 92, ISSN: 1944-186X, BUTTER® ID: 015304011

From the newsletter Journal of Robotics & Machine Learning.
https://www.newsrx.com/Butter/#!Search:a=15304011


This is a NewsRx® article created by NewsRx® and posted by NewsRx®. As proof that we are NewsRx® posting NewsRx® content, we have added a link to this steemit page on our main corporate website. The link is at the bottom left under "site links" at https://www.newsrx.com/NewsRxCorp/.

We have been in business for more than 20 years and our full contact information is available on our main corporate website.

We only upvote our posts after at least one other user has upvoted the article to increase the curation awards of upvoters.

NewsRx® offers 195 weekly newsletters providing comprehensive information on all professional topics, ranging from health, pharma and life science to business, tech, energy, law, and finance. Our newsletters report only the most relevant and authoritative information from qualified sources.

View Newsletter Titles

About NewsRx® and Contact Information

Authors get paid when people like you upvote their post.
If you enjoyed what you read here, create your account today and start earning FREE STEEM!