FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4323664660> ?p ?o ?g. }

• W4323664660 endingPage "109514" @default.
• W4323664660 startingPage "109514" @default.
• W4323664660 abstract "In this paper, we present a lightweight Bi-level Recurrent Refinement Network (Bi-RRNet) for Camouflaged Object Detection (COD) that consists of a Lower-level RRNet (L-RRN) and an Up-level RRNet (U-RRN) to progressively refine the multi-level context features for precise dense prediction. In particular, the L-RRN recursively refines the deeper layer high-level semantic features with the high-resolution low-level features from the earlier layers in a top-down manner, and the U-RRN progressively polishes the refined features from the L-RRN in a recurrent manner, producing the high-resolution semantic features that are essential to accurate COD. Moreover, we develop a Multi-scale Scene Perception Module (MSPM) that, in order to deal with target appearance variation, first compresses the global scene context information at each layer into a learnable weight vector and then modulates the multi-scale context features produced by a filter bank with various local receptive fields using the learned weights. Meanwhile, we design a Region-Consistency Enhancement Module (RCEM) that makes use of high-level semantic features to direct filtering out the cluttered information in the lower-layer features. This module can highlight the regions of camouflaged objects, maximizing the inter-class contrast between the objects and their surroundings. Extensive experiments on four challenging benchmark datasets, including CHAMELEON, CAMO, COD10K, and NC4K, show that our Bi-RRNet outperforms a variety of state-of-the-art methods in terms of accuracy and model parameters. Our Bi-RRNet, in particular, is lightweight, with 14.95M parameters that are only half the size of the state-of-the-art BSA-Net." @default.
• W4323664660 created "2023-03-10" @default.
• W4323664660 creator A5021293751 @default.
• W4323664660 creator A5024793526 @default.
• W4323664660 creator A5024940009 @default.
• W4323664660 creator A5054433231 @default.
• W4323664660 creator A5075412755 @default.
• W4323664660 date "2023-07-01" @default.
• W4323664660 modified "2023-10-06" @default.
• W4323664660 title "Bi-RRNet: Bi-level recurrent refinement network for camouflaged object detection" @default.
• W4323664660 cites W1818190875 @default.
• W4323664660 cites W2092792357 @default.
• W4323664660 cites W2151040689 @default.
• W4323664660 cites W2912729634 @default.
• W4323664660 cites W2928165649 @default.
• W4323664660 cites W2937243219 @default.
• W4323664660 cites W2943545929 @default.
• W4323664660 cites W3000281486 @default.
• W4323664660 cites W3025800305 @default.
• W4323664660 cites W3033841690 @default.
• W4323664660 cites W3128340563 @default.
• W4323664660 cites W3129581972 @default.
• W4323664660 cites W3210073375 @default.
• W4323664660 cites W3211246039 @default.
• W4323664660 cites W4220880800 @default.
• W4323664660 doi "https://doi.org/10.1016/j.patcog.2023.109514" @default.
• W4323664660 hasPublicationYear "2023" @default.
• W4323664660 type Work @default.
• W4323664660 citedByCount "1" @default.
• W4323664660 countsByYear W43236646602023 @default.
• W4323664660 crossrefType "journal-article" @default.
• W4323664660 hasAuthorship W4323664660A5021293751 @default.
• W4323664660 hasAuthorship W4323664660A5024793526 @default.
• W4323664660 hasAuthorship W4323664660A5024940009 @default.
• W4323664660 hasAuthorship W4323664660A5054433231 @default.
• W4323664660 hasAuthorship W4323664660A5075412755 @default.
• W4323664660 hasConcept C106131492 @default.
• W4323664660 hasConcept C121332964 @default.
• W4323664660 hasConcept C13280743 @default.
• W4323664660 hasConcept C151730666 @default.
• W4323664660 hasConcept C153180895 @default.
• W4323664660 hasConcept C154945302 @default.
• W4323664660 hasConcept C178790620 @default.
• W4323664660 hasConcept C185592680 @default.
• W4323664660 hasConcept C185798385 @default.
• W4323664660 hasConcept C205649164 @default.
• W4323664660 hasConcept C2776436953 @default.
• W4323664660 hasConcept C2777212361 @default.
• W4323664660 hasConcept C2778755073 @default.
• W4323664660 hasConcept C2779227376 @default.
• W4323664660 hasConcept C2779343474 @default.
• W4323664660 hasConcept C2781238097 @default.
• W4323664660 hasConcept C31258907 @default.
• W4323664660 hasConcept C31972630 @default.
• W4323664660 hasConcept C41008148 @default.
• W4323664660 hasConcept C62520636 @default.
• W4323664660 hasConcept C86803240 @default.
• W4323664660 hasConcept C88796919 @default.
• W4323664660 hasConceptScore W4323664660C106131492 @default.
• W4323664660 hasConceptScore W4323664660C121332964 @default.
• W4323664660 hasConceptScore W4323664660C13280743 @default.
• W4323664660 hasConceptScore W4323664660C151730666 @default.
• W4323664660 hasConceptScore W4323664660C153180895 @default.
• W4323664660 hasConceptScore W4323664660C154945302 @default.
• W4323664660 hasConceptScore W4323664660C178790620 @default.
• W4323664660 hasConceptScore W4323664660C185592680 @default.
• W4323664660 hasConceptScore W4323664660C185798385 @default.
• W4323664660 hasConceptScore W4323664660C205649164 @default.
• W4323664660 hasConceptScore W4323664660C2776436953 @default.
• W4323664660 hasConceptScore W4323664660C2777212361 @default.
• W4323664660 hasConceptScore W4323664660C2778755073 @default.
• W4323664660 hasConceptScore W4323664660C2779227376 @default.
• W4323664660 hasConceptScore W4323664660C2779343474 @default.
• W4323664660 hasConceptScore W4323664660C2781238097 @default.
• W4323664660 hasConceptScore W4323664660C31258907 @default.
• W4323664660 hasConceptScore W4323664660C31972630 @default.
• W4323664660 hasConceptScore W4323664660C41008148 @default.
• W4323664660 hasConceptScore W4323664660C62520636 @default.
• W4323664660 hasConceptScore W4323664660C86803240 @default.
• W4323664660 hasConceptScore W4323664660C88796919 @default.
• W4323664660 hasFunder F4320321001 @default.
• W4323664660 hasFunder F4320324849 @default.
• W4323664660 hasLocation W43236646601 @default.
• W4323664660 hasOpenAccess W4323664660 @default.
• W4323664660 hasPrimaryLocation W43236646601 @default.
• W4323664660 hasRelatedWork W1837097281 @default.
• W4323664660 hasRelatedWork W1966410754 @default.
• W4323664660 hasRelatedWork W2007544051 @default.
• W4323664660 hasRelatedWork W2030539674 @default.
• W4323664660 hasRelatedWork W2095705906 @default.
• W4323664660 hasRelatedWork W2325242284 @default.
• W4323664660 hasRelatedWork W2363840281 @default.
• W4323664660 hasRelatedWork W2732308154 @default.
• W4323664660 hasRelatedWork W2789220062 @default.
• W4323664660 hasRelatedWork W2975200075 @default.
• W4323664660 hasVolume "139" @default.
• W4323664660 isParatext "false" @default.
• W4323664660 isRetracted "false" @default.

• next