FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2945164022> ?p ?o ?g. }

• W2945164022 abstract "The Convolutional Neural Networks (CNNs) generate the feature representation of complex objects by collecting hierarchical and different parts of semantic sub-features. These sub-features can usually be distributed in grouped form in the feature vector of each layer, representing various semantic entities. However, the activation of these sub-features is often spatially affected by similar patterns and noisy backgrounds, resulting in erroneous localization and identification. We propose a Spatial Group-wise Enhance (SGE) module that can adjust the importance of each sub-feature by generating an attention factor for each spatial location in each semantic group, so that every individual group can autonomously enhance its learnt expression and suppress possible noise. The attention factors are only guided by the similarities between the global and local feature descriptors inside each group, thus the design of SGE module is extremely lightweight with emph{almost no extra parameters and calculations}. Despite being trained with only category supervisions, the SGE component is extremely effective in highlighting multiple active areas with various high-order semantics (such as the dog's eyes, nose, etc.). When integrated with popular CNN backbones, SGE can significantly boost the performance of image recognition tasks. Specifically, based on ResNet50 backbones, SGE achieves 1.2% Top-1 accuracy improvement on the ImageNet benchmark and 1.0$sim$2.0% AP gain on the COCO benchmark across a wide range of detectors (Faster/Mask/Cascade RCNN and RetinaNet). Codes and pretrained models are available at this https URL." @default.
• W2945164022 created "2019-05-29" @default.
• W2945164022 creator A5004579631 @default.
• W2945164022 creator A5045603863 @default.
• W2945164022 creator A5052636016 @default.
• W2945164022 date "2019-05-23" @default.
• W2945164022 modified "2023-09-27" @default.
• W2945164022 title "Spatial Group-wise Enhance: Improving Semantic Feature Learning in Convolutional Networks" @default.
• W2945164022 cites W1677182931 @default.
• W2945164022 cites W1686810756 @default.
• W2945164022 cites W1861492603 @default.
• W2945164022 cites W2097117768 @default.
• W2945164022 cites W2117539524 @default.
• W2945164022 cites W2135254996 @default.
• W2945164022 cites W2151103935 @default.
• W2945164022 cites W2154579312 @default.
• W2945164022 cites W2161969291 @default.
• W2945164022 cites W2163605009 @default.
• W2945164022 cites W2183341477 @default.
• W2945164022 cites W2194775991 @default.
• W2945164022 cites W2302255633 @default.
• W2945164022 cites W2549139847 @default.
• W2945164022 cites W2551396370 @default.
• W2945164022 cites W2565639579 @default.
• W2945164022 cites W2612445135 @default.
• W2945164022 cites W2613718673 @default.
• W2945164022 cites W2796438033 @default.
• W2945164022 cites W2866634454 @default.
• W2945164022 cites W2883780447 @default.
• W2945164022 cites W2884030607 @default.
• W2945164022 cites W2884585870 @default.
• W2945164022 cites W2922509574 @default.
• W2945164022 cites W2928165649 @default.
• W2945164022 cites W2944779197 @default.
• W2945164022 cites W2949117887 @default.
• W2945164022 cites W2962943776 @default.
• W2945164022 cites W2962965405 @default.
• W2945164022 cites W2963030892 @default.
• W2945164022 cites W2963091558 @default.
• W2945164022 cites W2963125010 @default.
• W2945164022 cites W2963150697 @default.
• W2945164022 cites W2963351448 @default.
• W2945164022 cites W2963403868 @default.
• W2945164022 cites W2963420686 @default.
• W2945164022 cites W2963446712 @default.
• W2945164022 cites W2963495494 @default.
• W2945164022 cites W2963703618 @default.
• W2945164022 cites W2963843116 @default.
• W2945164022 cites W2964241181 @default.
• W2945164022 cites W2964308564 @default.
• W2945164022 cites W2982220924 @default.
• W2945164022 cites W3048030262 @default.
• W2945164022 hasPublicationYear "2019" @default.
• W2945164022 type Work @default.
• W2945164022 sameAs 2945164022 @default.
• W2945164022 citedByCount "20" @default.
• W2945164022 countsByYear W29451640222019 @default.
• W2945164022 countsByYear W29451640222020 @default.
• W2945164022 countsByYear W29451640222021 @default.
• W2945164022 crossrefType "posted-content" @default.
• W2945164022 hasAuthorship W2945164022A5004579631 @default.
• W2945164022 hasAuthorship W2945164022A5045603863 @default.
• W2945164022 hasAuthorship W2945164022A5052636016 @default.
• W2945164022 hasConcept C138885662 @default.
• W2945164022 hasConcept C153180895 @default.
• W2945164022 hasConcept C154945302 @default.
• W2945164022 hasConcept C17744445 @default.
• W2945164022 hasConcept C184337299 @default.
• W2945164022 hasConcept C185798385 @default.
• W2945164022 hasConcept C199360897 @default.
• W2945164022 hasConcept C199539241 @default.
• W2945164022 hasConcept C205649164 @default.
• W2945164022 hasConcept C2776359362 @default.
• W2945164022 hasConcept C2776401178 @default.
• W2945164022 hasConcept C41008148 @default.
• W2945164022 hasConcept C41895202 @default.
• W2945164022 hasConcept C58640448 @default.
• W2945164022 hasConcept C81363708 @default.
• W2945164022 hasConcept C94625758 @default.
• W2945164022 hasConceptScore W2945164022C138885662 @default.
• W2945164022 hasConceptScore W2945164022C153180895 @default.
• W2945164022 hasConceptScore W2945164022C154945302 @default.
• W2945164022 hasConceptScore W2945164022C17744445 @default.
• W2945164022 hasConceptScore W2945164022C184337299 @default.
• W2945164022 hasConceptScore W2945164022C185798385 @default.
• W2945164022 hasConceptScore W2945164022C199360897 @default.
• W2945164022 hasConceptScore W2945164022C199539241 @default.
• W2945164022 hasConceptScore W2945164022C205649164 @default.
• W2945164022 hasConceptScore W2945164022C2776359362 @default.
• W2945164022 hasConceptScore W2945164022C2776401178 @default.
• W2945164022 hasConceptScore W2945164022C41008148 @default.
• W2945164022 hasConceptScore W2945164022C41895202 @default.
• W2945164022 hasConceptScore W2945164022C58640448 @default.
• W2945164022 hasConceptScore W2945164022C81363708 @default.
• W2945164022 hasConceptScore W2945164022C94625758 @default.
• W2945164022 hasLocation W29451640221 @default.
• W2945164022 hasOpenAccess W2945164022 @default.
• W2945164022 hasPrimaryLocation W29451640221 @default.
• W2945164022 hasRelatedWork W1861492603 @default.
• W2945164022 hasRelatedWork W2108598243 @default.

• next