Matches in SemOpenAlex for { <https://semopenalex.org/work/W3194834807> ?p ?o ?g. }
- W3194834807 abstract "Most of the existing object detection methods generate poor glass detection results, due to the fact that the transparent glass shares the same appearance with arbitrary objects behind it in an image. Different from traditional deep learning-based wisdoms that simply use the object boundary as auxiliary supervision, we exploit label decoupling to decompose the original labeled ground-truth (GT) map into an interior-diffusion map and a boundary-diffusion map. The GT map in collaboration with the two newly generated maps breaks the imbalanced distribution of the object boundary, leading to improved glass detection quality. We have three key contributions to solve the transparent glass detection problem: (1) We propose a three-stream neural network (call GlassNet for short) to fully absorb beneficial features in the three maps. (2) We design a multi-scale interactive dilation module to explore a wider range of contextual information. (3) We develop an attention-based boundary-aware feature Mosaic module to integrate multi-modal information. Extensive experiments on the benchmark dataset exhibit clear improvements of our method over SOTAs, in terms of both the overall glass detection accuracy and boundary clearness." @default.
- W3194834807 created "2021-08-30" @default.
- W3194834807 creator A5013151488 @default.
- W3194834807 creator A5019758816 @default.
- W3194834807 creator A5029780082 @default.
- W3194834807 creator A5040099999 @default.
- W3194834807 creator A5051555459 @default.
- W3194834807 creator A5071638388 @default.
- W3194834807 creator A5082236680 @default.
- W3194834807 creator A5091482685 @default.
- W3194834807 date "2021-08-25" @default.
- W3194834807 modified "2023-09-23" @default.
- W3194834807 title "GlassNet: Label Decoupling-based Three-stream Neural Network for Robust Image Glass Detection" @default.
- W3194834807 cites W1686810756 @default.
- W3194834807 cites W1903029394 @default.
- W3194834807 cites W2039313011 @default.
- W3194834807 cites W2047670868 @default.
- W3194834807 cites W2100470808 @default.
- W3194834807 cites W2161236525 @default.
- W3194834807 cites W2194775991 @default.
- W3194834807 cites W2206865673 @default.
- W3194834807 cites W2211996548 @default.
- W3194834807 cites W2412782625 @default.
- W3194834807 cites W2560023338 @default.
- W3194834807 cites W2626778328 @default.
- W3194834807 cites W2630837129 @default.
- W3194834807 cites W2780708736 @default.
- W3194834807 cites W2798791651 @default.
- W3194834807 cites W2798791840 @default.
- W3194834807 cites W2798825526 @default.
- W3194834807 cites W2799213142 @default.
- W3194834807 cites W2884555738 @default.
- W3194834807 cites W2886934227 @default.
- W3194834807 cites W2895126795 @default.
- W3194834807 cites W2895251968 @default.
- W3194834807 cites W2895340641 @default.
- W3194834807 cites W2938260698 @default.
- W3194834807 cites W2945444597 @default.
- W3194834807 cites W2955058313 @default.
- W3194834807 cites W2961348656 @default.
- W3194834807 cites W2962914239 @default.
- W3194834807 cites W2963032190 @default.
- W3194834807 cites W2963091558 @default.
- W3194834807 cites W2963112696 @default.
- W3194834807 cites W2963299740 @default.
- W3194834807 cites W2963706010 @default.
- W3194834807 cites W2963727650 @default.
- W3194834807 cites W2963753350 @default.
- W3194834807 cites W2981689412 @default.
- W3194834807 cites W2983727866 @default.
- W3194834807 cites W2990984982 @default.
- W3194834807 cites W3034185160 @default.
- W3194834807 cites W3034592098 @default.
- W3194834807 cites W3035290198 @default.
- W3194834807 cites W3035422681 @default.
- W3194834807 cites W3035618398 @default.
- W3194834807 cites W3096609285 @default.
- W3194834807 cites W3103611212 @default.
- W3194834807 cites W3174982506 @default.
- W3194834807 doi "https://doi.org/10.48550/arxiv.2108.11117" @default.
- W3194834807 hasPublicationYear "2021" @default.
- W3194834807 type Work @default.
- W3194834807 sameAs 3194834807 @default.
- W3194834807 citedByCount "0" @default.
- W3194834807 crossrefType "posted-content" @default.
- W3194834807 hasAuthorship W3194834807A5013151488 @default.
- W3194834807 hasAuthorship W3194834807A5019758816 @default.
- W3194834807 hasAuthorship W3194834807A5029780082 @default.
- W3194834807 hasAuthorship W3194834807A5040099999 @default.
- W3194834807 hasAuthorship W3194834807A5051555459 @default.
- W3194834807 hasAuthorship W3194834807A5071638388 @default.
- W3194834807 hasAuthorship W3194834807A5082236680 @default.
- W3194834807 hasAuthorship W3194834807A5091482685 @default.
- W3194834807 hasBestOaLocation W31948348071 @default.
- W3194834807 hasConcept C115961682 @default.
- W3194834807 hasConcept C127413603 @default.
- W3194834807 hasConcept C13280743 @default.
- W3194834807 hasConcept C133731056 @default.
- W3194834807 hasConcept C134306372 @default.
- W3194834807 hasConcept C146849305 @default.
- W3194834807 hasConcept C153180895 @default.
- W3194834807 hasConcept C154945302 @default.
- W3194834807 hasConcept C165696696 @default.
- W3194834807 hasConcept C185798385 @default.
- W3194834807 hasConcept C205606062 @default.
- W3194834807 hasConcept C205649164 @default.
- W3194834807 hasConcept C2524010 @default.
- W3194834807 hasConcept C2776151529 @default.
- W3194834807 hasConcept C2780757906 @default.
- W3194834807 hasConcept C31972630 @default.
- W3194834807 hasConcept C33923547 @default.
- W3194834807 hasConcept C38652104 @default.
- W3194834807 hasConcept C41008148 @default.
- W3194834807 hasConcept C50644808 @default.
- W3194834807 hasConcept C62354387 @default.
- W3194834807 hasConceptScore W3194834807C115961682 @default.
- W3194834807 hasConceptScore W3194834807C127413603 @default.
- W3194834807 hasConceptScore W3194834807C13280743 @default.
- W3194834807 hasConceptScore W3194834807C133731056 @default.
- W3194834807 hasConceptScore W3194834807C134306372 @default.