Matches in SemOpenAlex for { <https://semopenalex.org/work/W3206399630> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W3206399630 abstract "As the conventional activation functions such as ReLU, LeakyReLU, and PReLU, the negative parts in feature maps are simply truncated or linearized, which may result in unflexible structure and undesired information distortion. In this paper, we propose a simple but effective Bilateral Activation Mechanism (BAM) which could be applied to the activation function to offer an efficient feature extraction model. Based on BAM, the Bilateral ReLU Residual Block (BRRB) that still sufficiently keeps the nonlinear characteristic of ReLU is constructed to separate the feature maps into two parts, i.e., the positive and negative components, then adaptively represent and extract the features by two independent convolution layers. Besides, our mechanism will not increase any extra parameters or computational burden in the network. We finally embed the BRRB into a basic ResNet architecture, called BRResNet, it is easy to obtain state-of-the-art performance in two image fusion tasks, i.e., pansharpening and hyperspectral image super-resolution (HISR). Additionally, deeper analysis and ablation study demonstrate the effectiveness of BAM, the lightweight property of the network, etc. Please find the code from the project page1 https://liangjiandeng.github.io/Projects_Res/bam_mm2021.html" @default.
- W3206399630 created "2021-10-25" @default.
- W3206399630 creator A5022927694 @default.
- W3206399630 creator A5068556247 @default.
- W3206399630 creator A5069340514 @default.
- W3206399630 creator A5088224232 @default.
- W3206399630 date "2021-10-17" @default.
- W3206399630 modified "2023-10-16" @default.
- W3206399630 title "BAM" @default.
- W3206399630 cites W1495168473 @default.
- W3206399630 cites W1677182931 @default.
- W3206399630 cites W1916874600 @default.
- W3206399630 cites W1991460509 @default.
- W3206399630 cites W2001800591 @default.
- W3206399630 cites W2012946078 @default.
- W3206399630 cites W2021046129 @default.
- W3206399630 cites W2033021901 @default.
- W3206399630 cites W2100109944 @default.
- W3206399630 cites W2100329651 @default.
- W3206399630 cites W2123046940 @default.
- W3206399630 cites W2124743705 @default.
- W3206399630 cites W2133665775 @default.
- W3206399630 cites W2142843085 @default.
- W3206399630 cites W2171211028 @default.
- W3206399630 cites W2172185514 @default.
- W3206399630 cites W2194775991 @default.
- W3206399630 cites W2327302159 @default.
- W3206399630 cites W2507697802 @default.
- W3206399630 cites W2767014298 @default.
- W3206399630 cites W2777033955 @default.
- W3206399630 cites W2803614623 @default.
- W3206399630 cites W2804744787 @default.
- W3206399630 cites W2945202593 @default.
- W3206399630 cites W2963007295 @default.
- W3206399630 cites W2964275574 @default.
- W3206399630 cites W3016410830 @default.
- W3206399630 cites W3029812440 @default.
- W3206399630 cites W3093334928 @default.
- W3206399630 cites W3099843321 @default.
- W3206399630 cites W3105328221 @default.
- W3206399630 doi "https://doi.org/10.1145/3474085.3475571" @default.
- W3206399630 hasPublicationYear "2021" @default.
- W3206399630 type Work @default.
- W3206399630 sameAs 3206399630 @default.
- W3206399630 citedByCount "14" @default.
- W3206399630 countsByYear W32063996302022 @default.
- W3206399630 countsByYear W32063996302023 @default.
- W3206399630 crossrefType "proceedings-article" @default.
- W3206399630 hasAuthorship W3206399630A5022927694 @default.
- W3206399630 hasAuthorship W3206399630A5068556247 @default.
- W3206399630 hasAuthorship W3206399630A5069340514 @default.
- W3206399630 hasAuthorship W3206399630A5088224232 @default.
- W3206399630 hasConcept C41008148 @default.
- W3206399630 hasConceptScore W3206399630C41008148 @default.
- W3206399630 hasFunder F4320335777 @default.
- W3206399630 hasLocation W32063996301 @default.
- W3206399630 hasOpenAccess W3206399630 @default.
- W3206399630 hasPrimaryLocation W32063996301 @default.
- W3206399630 hasRelatedWork W2093578348 @default.
- W3206399630 hasRelatedWork W2350741829 @default.
- W3206399630 hasRelatedWork W2358668433 @default.
- W3206399630 hasRelatedWork W2376932109 @default.
- W3206399630 hasRelatedWork W2382290278 @default.
- W3206399630 hasRelatedWork W2390279801 @default.
- W3206399630 hasRelatedWork W2748952813 @default.
- W3206399630 hasRelatedWork W2766271392 @default.
- W3206399630 hasRelatedWork W2899084033 @default.
- W3206399630 hasRelatedWork W3004735627 @default.
- W3206399630 isParatext "false" @default.
- W3206399630 isRetracted "false" @default.
- W3206399630 magId "3206399630" @default.
- W3206399630 workType "article" @default.