Matches in SemOpenAlex for { <https://semopenalex.org/work/W2997471409> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W2997471409 endingPage "12588" @default.
- W2997471409 startingPage "12581" @default.
- W2997471409 abstract "We propose a simple yet effective method to reduce the redundancy of DenseNet by substantially decreasing the number of stacked modules by replacing the original bottleneck by our SMG module, which is augmented by local residual. Furthermore, SMG module is equipped with an efficient two-stage pipeline, which aims to DenseNet-like architectures that need to integrate all previous outputs, i.e., squeezing the incoming informative but redundant features gradually by hierarchical convolutions as a hourglass shape and then exciting it by multi-kernel depthwise convolutions, the output of which would be compact and hold more informative multi-scale features. We further develop a forget and an update gate by introducing the popular attention modules to implement the effective fusion instead of a simple addition between reused and new features. Due to the Hybrid Connectivity (nested combination of global dense and local residual) and Gated mechanisms, we called our network as the HCGNet. Experimental results on CIFAR and ImageNet datasets show that HCGNet is more prominently efficient than DenseNet, and can also significantly outperform state-of-the-art networks with less complexity. Moreover, HCGNet also shows the remarkable interpretability and robustness by network dissection and adversarial defense, respectively. On MS-COCO, HCGNet can consistently learn better features than popular backbones." @default.
- W2997471409 created "2020-01-10" @default.
- W2997471409 creator A5016038041 @default.
- W2997471409 creator A5019534297 @default.
- W2997471409 creator A5029335824 @default.
- W2997471409 creator A5046293929 @default.
- W2997471409 creator A5054925898 @default.
- W2997471409 creator A5055016576 @default.
- W2997471409 creator A5073094530 @default.
- W2997471409 creator A5085502749 @default.
- W2997471409 date "2020-04-03" @default.
- W2997471409 modified "2023-10-14" @default.
- W2997471409 title "Gated Convolutional Networks with Hybrid Connectivity for Image Classification" @default.
- W2997471409 doi "https://doi.org/10.1609/aaai.v34i07.6948" @default.
- W2997471409 hasPublicationYear "2020" @default.
- W2997471409 type Work @default.
- W2997471409 sameAs 2997471409 @default.
- W2997471409 citedByCount "21" @default.
- W2997471409 countsByYear W29974714092020 @default.
- W2997471409 countsByYear W29974714092021 @default.
- W2997471409 countsByYear W29974714092022 @default.
- W2997471409 countsByYear W29974714092023 @default.
- W2997471409 crossrefType "journal-article" @default.
- W2997471409 hasAuthorship W2997471409A5016038041 @default.
- W2997471409 hasAuthorship W2997471409A5019534297 @default.
- W2997471409 hasAuthorship W2997471409A5029335824 @default.
- W2997471409 hasAuthorship W2997471409A5046293929 @default.
- W2997471409 hasAuthorship W2997471409A5054925898 @default.
- W2997471409 hasAuthorship W2997471409A5055016576 @default.
- W2997471409 hasAuthorship W2997471409A5073094530 @default.
- W2997471409 hasAuthorship W2997471409A5085502749 @default.
- W2997471409 hasBestOaLocation W29974714091 @default.
- W2997471409 hasConcept C104317684 @default.
- W2997471409 hasConcept C111472728 @default.
- W2997471409 hasConcept C111919701 @default.
- W2997471409 hasConcept C11413529 @default.
- W2997471409 hasConcept C138885662 @default.
- W2997471409 hasConcept C149635348 @default.
- W2997471409 hasConcept C152124472 @default.
- W2997471409 hasConcept C153180895 @default.
- W2997471409 hasConcept C154945302 @default.
- W2997471409 hasConcept C155512373 @default.
- W2997471409 hasConcept C185592680 @default.
- W2997471409 hasConcept C199360897 @default.
- W2997471409 hasConcept C2780513914 @default.
- W2997471409 hasConcept C2780586882 @default.
- W2997471409 hasConcept C2781067378 @default.
- W2997471409 hasConcept C41008148 @default.
- W2997471409 hasConcept C43521106 @default.
- W2997471409 hasConcept C46686674 @default.
- W2997471409 hasConcept C55493867 @default.
- W2997471409 hasConcept C63479239 @default.
- W2997471409 hasConcept C81363708 @default.
- W2997471409 hasConceptScore W2997471409C104317684 @default.
- W2997471409 hasConceptScore W2997471409C111472728 @default.
- W2997471409 hasConceptScore W2997471409C111919701 @default.
- W2997471409 hasConceptScore W2997471409C11413529 @default.
- W2997471409 hasConceptScore W2997471409C138885662 @default.
- W2997471409 hasConceptScore W2997471409C149635348 @default.
- W2997471409 hasConceptScore W2997471409C152124472 @default.
- W2997471409 hasConceptScore W2997471409C153180895 @default.
- W2997471409 hasConceptScore W2997471409C154945302 @default.
- W2997471409 hasConceptScore W2997471409C155512373 @default.
- W2997471409 hasConceptScore W2997471409C185592680 @default.
- W2997471409 hasConceptScore W2997471409C199360897 @default.
- W2997471409 hasConceptScore W2997471409C2780513914 @default.
- W2997471409 hasConceptScore W2997471409C2780586882 @default.
- W2997471409 hasConceptScore W2997471409C2781067378 @default.
- W2997471409 hasConceptScore W2997471409C41008148 @default.
- W2997471409 hasConceptScore W2997471409C43521106 @default.
- W2997471409 hasConceptScore W2997471409C46686674 @default.
- W2997471409 hasConceptScore W2997471409C55493867 @default.
- W2997471409 hasConceptScore W2997471409C63479239 @default.
- W2997471409 hasConceptScore W2997471409C81363708 @default.
- W2997471409 hasIssue "07" @default.
- W2997471409 hasLocation W29974714091 @default.
- W2997471409 hasLocation W29974714092 @default.
- W2997471409 hasOpenAccess W2997471409 @default.
- W2997471409 hasPrimaryLocation W29974714091 @default.
- W2997471409 hasRelatedWork W2003125512 @default.
- W2997471409 hasRelatedWork W2340694410 @default.
- W2997471409 hasRelatedWork W2543725295 @default.
- W2997471409 hasRelatedWork W2767651786 @default.
- W2997471409 hasRelatedWork W2809283485 @default.
- W2997471409 hasRelatedWork W2897195263 @default.
- W2997471409 hasRelatedWork W2912288872 @default.
- W2997471409 hasRelatedWork W4205427372 @default.
- W2997471409 hasRelatedWork W4293768783 @default.
- W2997471409 hasRelatedWork W4310880831 @default.
- W2997471409 hasVolume "34" @default.
- W2997471409 isParatext "false" @default.
- W2997471409 isRetracted "false" @default.
- W2997471409 magId "2997471409" @default.
- W2997471409 workType "article" @default.