FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285114594> ?p ?o ?g. }

• W4285114594 endingPage "62810" @default.
• W4285114594 startingPage "62800" @default.
• W4285114594 abstract "In fine-grained visual classification(FGVC), the small inter-class variations and the large intra-class variations are always inherent attributes, so it is much more challenging than traditional classification tasks. Recent works mainly tackle this problem by employing attention mechanisms to locate the most discriminative parts. However, these methods tend to neglect other inconspicuous but distinguishable parts, and can not effectively fuse the features information of different scales and different degrees of discrimination. In this work, we propose a multi-scale progressive complementary fusion network (MPCF-Net) to tackle these problems. In particular, we propose: (i) A three-step multi-scale progressive training method, which employs the image slicer to generate puzzle images at different scales followed by multi-step progressive training. This enables the network to capture multi-granularity local feature information and gradually expand its attention to the global structural information as the training progresses for multi-granularity information fusion. (ii) A plug-and-play feature complementary enhancement module (FCEM) that explicitly enhances the features extracted by the current layer of the network, while also enabling the next layer of the network to extract potential complementary feature information to diversify the features. Our experiments were conducted on four FGVC benchmark datasets and yielded state-of-the-art or competitive results." @default.
• W4285114594 created "2022-07-14" @default.
• W4285114594 creator A5051645697 @default.
• W4285114594 creator A5058235577 @default.
• W4285114594 creator A5065496543 @default.
• W4285114594 date "2022-01-01" @default.
• W4285114594 modified "2023-10-14" @default.
• W4285114594 title "Multi-scale Progressive Complementary Fusion Network for Fine-Grained Visual Classification" @default.
• W4285114594 cites W1955942245 @default.
• W4285114594 cites W2104657103 @default.
• W4285114594 cites W2194775991 @default.
• W4285114594 cites W2202499615 @default.
• W4285114594 cites W2462457117 @default.
• W4285114594 cites W2530289846 @default.
• W4285114594 cites W2737725206 @default.
• W4285114594 cites W2740620254 @default.
• W4285114594 cites W2741910023 @default.
• W4285114594 cites W2763070548 @default.
• W4285114594 cites W2773003563 @default.
• W4285114594 cites W2798365843 @default.
• W4285114594 cites W2807931652 @default.
• W4285114594 cites W2891951760 @default.
• W4285114594 cites W2940925558 @default.
• W4285114594 cites W2961018736 @default.
• W4285114594 cites W2963407932 @default.
• W4285114594 cites W2964042923 @default.
• W4285114594 cites W2982041717 @default.
• W4285114594 cites W2986821660 @default.
• W4285114594 cites W2990495699 @default.
• W4285114594 cites W2997426000 @default.
• W4285114594 cites W2998345525 @default.
• W4285114594 cites W2998619563 @default.
• W4285114594 cites W3008809756 @default.
• W4285114594 cites W3009073662 @default.
• W4285114594 cites W3035367622 @default.
• W4285114594 cites W3099903704 @default.
• W4285114594 cites W3108870912 @default.
• W4285114594 cites W3124951096 @default.
• W4285114594 cites W3140405497 @default.
• W4285114594 cites W3157251352 @default.
• W4285114594 cites W3200659198 @default.
• W4285114594 cites W3200944276 @default.
• W4285114594 cites W4200355216 @default.
• W4285114594 cites W4207054665 @default.
• W4285114594 cites W56385144 @default.
• W4285114594 doi "https://doi.org/10.1109/access.2022.3179358" @default.
• W4285114594 hasPublicationYear "2022" @default.
• W4285114594 type Work @default.
• W4285114594 citedByCount "0" @default.
• W4285114594 crossrefType "journal-article" @default.
• W4285114594 hasAuthorship W4285114594A5051645697 @default.
• W4285114594 hasAuthorship W4285114594A5058235577 @default.
• W4285114594 hasAuthorship W4285114594A5065496543 @default.
• W4285114594 hasBestOaLocation W42851145941 @default.
• W4285114594 hasConcept C111919701 @default.
• W4285114594 hasConcept C119599485 @default.
• W4285114594 hasConcept C119857082 @default.
• W4285114594 hasConcept C121332964 @default.
• W4285114594 hasConcept C124101348 @default.
• W4285114594 hasConcept C127413603 @default.
• W4285114594 hasConcept C13280743 @default.
• W4285114594 hasConcept C138885662 @default.
• W4285114594 hasConcept C141353440 @default.
• W4285114594 hasConcept C153180895 @default.
• W4285114594 hasConcept C154945302 @default.
• W4285114594 hasConcept C177774035 @default.
• W4285114594 hasConcept C185798385 @default.
• W4285114594 hasConcept C205649164 @default.
• W4285114594 hasConcept C2776401178 @default.
• W4285114594 hasConcept C2777212361 @default.
• W4285114594 hasConcept C2778755073 @default.
• W4285114594 hasConcept C36464697 @default.
• W4285114594 hasConcept C41008148 @default.
• W4285114594 hasConcept C41895202 @default.
• W4285114594 hasConcept C52622490 @default.
• W4285114594 hasConcept C62520636 @default.
• W4285114594 hasConcept C97931131 @default.
• W4285114594 hasConceptScore W4285114594C111919701 @default.
• W4285114594 hasConceptScore W4285114594C119599485 @default.
• W4285114594 hasConceptScore W4285114594C119857082 @default.
• W4285114594 hasConceptScore W4285114594C121332964 @default.
• W4285114594 hasConceptScore W4285114594C124101348 @default.
• W4285114594 hasConceptScore W4285114594C127413603 @default.
• W4285114594 hasConceptScore W4285114594C13280743 @default.
• W4285114594 hasConceptScore W4285114594C138885662 @default.
• W4285114594 hasConceptScore W4285114594C141353440 @default.
• W4285114594 hasConceptScore W4285114594C153180895 @default.
• W4285114594 hasConceptScore W4285114594C154945302 @default.
• W4285114594 hasConceptScore W4285114594C177774035 @default.
• W4285114594 hasConceptScore W4285114594C185798385 @default.
• W4285114594 hasConceptScore W4285114594C205649164 @default.
• W4285114594 hasConceptScore W4285114594C2776401178 @default.
• W4285114594 hasConceptScore W4285114594C2777212361 @default.
• W4285114594 hasConceptScore W4285114594C2778755073 @default.
• W4285114594 hasConceptScore W4285114594C36464697 @default.
• W4285114594 hasConceptScore W4285114594C41008148 @default.
• W4285114594 hasConceptScore W4285114594C41895202 @default.
• W4285114594 hasConceptScore W4285114594C52622490 @default.

• next