Matches in SemOpenAlex for { <https://semopenalex.org/work/W4293790731> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4293790731 abstract "This paper focuses on the limitations of current over-parameterized shadow removal models. We present a novel lightweight deep neural network that processes shadow images in the LAB color space. The proposed network termed LAB-Net, is motivated by the following three observations: First, the LAB color space can well separate the luminance information and color properties. Second, sequentially-stacked convolutional layers fail to take full use of features from different receptive fields. Third, non-shadow regions are important prior knowledge to diminish the drastic color difference between shadow and non-shadow regions. Consequently, we design our LAB-Net by involving a two-branch structure: L and AB branches. Thus the shadow-related luminance information can well be processed in the L branch, while the color property is well retained in the AB branch. In addition, each branch is composed of several Basic Blocks, local spatial attention modules (LSA), and convolutional filters. Each Basic Block consists of multiple parallelized dilated convolutions of divergent dilation rates to receive different receptive fields that are operated with distinct network widths to save model parameters and computational costs. Then, an enhanced channel attention module (ECA) is constructed to aggregate features from different receptive fields for better shadow removal. Finally, the LSA modules are further developed to fully use the prior information in non-shadow regions to cleanse the shadow regions. We perform extensive experiments on the both ISTD and SRD datasets. Experimental results show that our LAB-Net well outperforms state-of-the-art methods. Also, our model's parameters and computational costs are reduced by several orders of magnitude. Our code is available at https://github.com/ngrxmu/LAB-Net." @default.
- W4293790731 created "2022-08-31" @default.
- W4293790731 creator A5000389309 @default.
- W4293790731 creator A5016080094 @default.
- W4293790731 creator A5017033486 @default.
- W4293790731 creator A5017100408 @default.
- W4293790731 creator A5026218314 @default.
- W4293790731 creator A5039883116 @default.
- W4293790731 creator A5086803311 @default.
- W4293790731 date "2022-08-27" @default.
- W4293790731 modified "2023-10-12" @default.
- W4293790731 title "LAB-Net: LAB Color-Space Oriented Lightweight Network for Shadow Removal" @default.
- W4293790731 doi "https://doi.org/10.48550/arxiv.2208.13039" @default.
- W4293790731 hasPublicationYear "2022" @default.
- W4293790731 type Work @default.
- W4293790731 citedByCount "0" @default.
- W4293790731 crossrefType "posted-content" @default.
- W4293790731 hasAuthorship W4293790731A5000389309 @default.
- W4293790731 hasAuthorship W4293790731A5016080094 @default.
- W4293790731 hasAuthorship W4293790731A5017033486 @default.
- W4293790731 hasAuthorship W4293790731A5017100408 @default.
- W4293790731 hasAuthorship W4293790731A5026218314 @default.
- W4293790731 hasAuthorship W4293790731A5039883116 @default.
- W4293790731 hasAuthorship W4293790731A5086803311 @default.
- W4293790731 hasBestOaLocation W42937907311 @default.
- W4293790731 hasConcept C115961682 @default.
- W4293790731 hasConcept C117797892 @default.
- W4293790731 hasConcept C121684516 @default.
- W4293790731 hasConcept C154945302 @default.
- W4293790731 hasConcept C15744967 @default.
- W4293790731 hasConcept C2524010 @default.
- W4293790731 hasConcept C2776326872 @default.
- W4293790731 hasConcept C2777210771 @default.
- W4293790731 hasConcept C2961294 @default.
- W4293790731 hasConcept C31972630 @default.
- W4293790731 hasConcept C33923547 @default.
- W4293790731 hasConcept C41008148 @default.
- W4293790731 hasConcept C542102704 @default.
- W4293790731 hasConcept C73313986 @default.
- W4293790731 hasConcept C81363708 @default.
- W4293790731 hasConceptScore W4293790731C115961682 @default.
- W4293790731 hasConceptScore W4293790731C117797892 @default.
- W4293790731 hasConceptScore W4293790731C121684516 @default.
- W4293790731 hasConceptScore W4293790731C154945302 @default.
- W4293790731 hasConceptScore W4293790731C15744967 @default.
- W4293790731 hasConceptScore W4293790731C2524010 @default.
- W4293790731 hasConceptScore W4293790731C2776326872 @default.
- W4293790731 hasConceptScore W4293790731C2777210771 @default.
- W4293790731 hasConceptScore W4293790731C2961294 @default.
- W4293790731 hasConceptScore W4293790731C31972630 @default.
- W4293790731 hasConceptScore W4293790731C33923547 @default.
- W4293790731 hasConceptScore W4293790731C41008148 @default.
- W4293790731 hasConceptScore W4293790731C542102704 @default.
- W4293790731 hasConceptScore W4293790731C73313986 @default.
- W4293790731 hasConceptScore W4293790731C81363708 @default.
- W4293790731 hasLocation W42937907311 @default.
- W4293790731 hasOpenAccess W4293790731 @default.
- W4293790731 hasPrimaryLocation W42937907311 @default.
- W4293790731 hasRelatedWork W2018981980 @default.
- W4293790731 hasRelatedWork W2041408572 @default.
- W4293790731 hasRelatedWork W2082464465 @default.
- W4293790731 hasRelatedWork W2133813344 @default.
- W4293790731 hasRelatedWork W2236660010 @default.
- W4293790731 hasRelatedWork W2368880388 @default.
- W4293790731 hasRelatedWork W2545619740 @default.
- W4293790731 hasRelatedWork W3014708372 @default.
- W4293790731 hasRelatedWork W3196422986 @default.
- W4293790731 hasRelatedWork W4361829754 @default.
- W4293790731 isParatext "false" @default.
- W4293790731 isRetracted "false" @default.
- W4293790731 workType "article" @default.