FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2970040664> ?p ?o ?g. }

• W2970040664 endingPage "123392" @default.
• W2970040664 startingPage "123367" @default.
• W2970040664 abstract "Existing fine-grained categorization methods predominantly conquer challenges independently, while neglecting the fact that patch proposal and feature extraction can reinforce each other. This necessitates to extract the domain-specific representations and localize key (most discriminative) patches alternately, since implicit to fine-grained specialization is the existence of an entry-category visual shared among all categories. In this study, an increasingly specialized perception convolutional neural network (ISP-CNN) is proposed, focusing on a butterfly domain at sub-species level due to the biosystematics structure. Its pipeline is an coarse-to-fine specialization that hierarchically extracts fine-scale features and proposes distinctive patches at multiple scales. Specifically, the framework consists of two highlights, i.e., hierarchical learning support vector machines (HL-SVMs) and patch proposal sub-networks (PPNs). Depending on the confidences obtained in HL-SVMs, the samples are classified at appropriate subset (i.e., sub-family, genus, and sub-species). Then the PPNs zoom the images to shift the focus on the most representational patches by taking previous predictions of HL-SVMs as a reference, while a finer scale network takes as input an amplified attended region from previous scales with gradual steps. As for self-optimization, ISP-CNN is driven by a patch-level loss and a class-level loss, to mutually learn patch proposals and decisions. For effectness verification, a total of 19,368 lab-made images of butterfly specimens spanning 48 sub-species are utilized as testing samples, while 116,208 augmented images are employed for training. ISP-CNN delivers the better or comparable performance, i.e., validation accuracy achieves 93.67% and testing accuracy achieves 92.13%, which outperforms state-of-the-arts." @default.
• W2970040664 created "2019-09-05" @default.
• W2970040664 creator A5013019306 @default.
• W2970040664 creator A5038344148 @default.
• W2970040664 creator A5039297893 @default.
• W2970040664 creator A5078092833 @default.
• W2970040664 date "2019-01-01" @default.
• W2970040664 modified "2023-09-24" @default.
• W2970040664 title "Increasingly Specialized Perception Network for Fine-Grained Visual Categorization of Butterfly Specimens" @default.
• W2970040664 cites W1536680647 @default.
• W2970040664 cites W1898560071 @default.
• W2970040664 cites W1905692714 @default.
• W2970040664 cites W1925596459 @default.
• W2970040664 cites W1948751323 @default.
• W2970040664 cites W1972252843 @default.
• W2970040664 cites W1972277333 @default.
• W2970040664 cites W1975976087 @default.
• W2970040664 cites W1994213117 @default.
• W2970040664 cites W2035009069 @default.
• W2970040664 cites W2050964073 @default.
• W2970040664 cites W2068562306 @default.
• W2970040664 cites W2088049833 @default.
• W2970040664 cites W2093125966 @default.
• W2970040664 cites W2097117768 @default.
• W2970040664 cites W2101391185 @default.
• W2970040664 cites W2102605133 @default.
• W2970040664 cites W2104657103 @default.
• W2970040664 cites W2108598243 @default.
• W2970040664 cites W2110765924 @default.
• W2970040664 cites W2138011018 @default.
• W2970040664 cites W2147800946 @default.
• W2970040664 cites W2152411181 @default.
• W2970040664 cites W2154422044 @default.
• W2970040664 cites W2155893237 @default.
• W2970040664 cites W2168356304 @default.
• W2970040664 cites W2173180041 @default.
• W2970040664 cites W2194775991 @default.
• W2970040664 cites W2202499615 @default.
• W2970040664 cites W2287418003 @default.
• W2970040664 cites W2289708887 @default.
• W2970040664 cites W2293070318 @default.
• W2970040664 cites W2296699367 @default.
• W2970040664 cites W2328317224 @default.
• W2970040664 cites W2460583509 @default.
• W2970040664 cites W2462457117 @default.
• W2970040664 cites W2479109623 @default.
• W2970040664 cites W2517543550 @default.
• W2970040664 cites W2533598788 @default.
• W2970040664 cites W2535410496 @default.
• W2970040664 cites W2543482215 @default.
• W2970040664 cites W2547954583 @default.
• W2970040664 cites W2549125172 @default.
• W2970040664 cites W2563812708 @default.
• W2970040664 cites W2604970008 @default.
• W2970040664 cites W2628684354 @default.
• W2970040664 cites W2715414385 @default.
• W2970040664 cites W2737725206 @default.
• W2970040664 cites W2752414151 @default.
• W2970040664 cites W2753713840 @default.
• W2970040664 cites W2755775504 @default.
• W2970040664 cites W2764076527 @default.
• W2970040664 cites W2765268259 @default.
• W2970040664 cites W2773003563 @default.
• W2970040664 cites W2806244818 @default.
• W2970040664 cites W2884739394 @default.
• W2970040664 cites W2885517796 @default.
• W2970040664 cites W2888868709 @default.
• W2970040664 cites W2891787551 @default.
• W2970040664 cites W2896572288 @default.
• W2970040664 cites W2896647254 @default.
• W2970040664 cites W2898041613 @default.
• W2970040664 cites W2899230946 @default.
• W2970040664 cites W2899438351 @default.
• W2970040664 cites W2908218113 @default.
• W2970040664 cites W2910363199 @default.
• W2970040664 cites W2915459603 @default.
• W2970040664 cites W2918956267 @default.
• W2970040664 cites W2963516811 @default.
• W2970040664 cites W2963758027 @default.
• W2970040664 cites W3105730638 @default.
• W2970040664 cites W3124951096 @default.
• W2970040664 cites W639708223 @default.
• W2970040664 cites W2061227176 @default.
• W2970040664 doi "https://doi.org/10.1109/access.2019.2938537" @default.
• W2970040664 hasPublicationYear "2019" @default.
• W2970040664 type Work @default.
• W2970040664 sameAs 2970040664 @default.
• W2970040664 citedByCount "5" @default.
• W2970040664 countsByYear W29700406642020 @default.
• W2970040664 countsByYear W29700406642021 @default.
• W2970040664 countsByYear W29700406642022 @default.
• W2970040664 crossrefType "journal-article" @default.
• W2970040664 hasAuthorship W2970040664A5013019306 @default.
• W2970040664 hasAuthorship W2970040664A5038344148 @default.
• W2970040664 hasAuthorship W2970040664A5039297893 @default.
• W2970040664 hasAuthorship W2970040664A5078092833 @default.
• W2970040664 hasBestOaLocation W29700406641 @default.
• W2970040664 hasConcept C154945302 @default.

• next