Matches in SemOpenAlex for { <https://semopenalex.org/work/W4205265212> ?p ?o ?g. }
- W4205265212 endingPage "224" @default.
- W4205265212 startingPage "213" @default.
- W4205265212 abstract "AbstractSemantic segmentation is widely used in robot perception and can be used for various subsequent tasks. Depth information has been proven to be a useful clue in the semantic segmentation of RGB-D images for providing a geometric counterpart to the RGB representation. At the same time, considering the importance of object boundaries in the robot’s perception process, it is very necessary to add attention to the boundaries of the objects in the semantic segmentation model.In this paper, we propose Efficient Boundary-Aware Network (EBANet) which relies on both RGB and depth images as input. We design a boundary attention branch to extract more boundary features of objects in the scene and generate boundary labels for supervision by a Canny edge detector. We also adopt a hybrid loss function fusing Cross-Entropy (CE) and structural similarity (SSIM) loss to guide the network to learn the transformation between the input image and the ground truth at the pixel and patch level. We evaluate our proposed EBANet on the common RGB-D dataset NYUv2 and show that we reach the state-of-the-art performance.KeywordsRGB-D semantic segmentationBoundary attentionHybrid loss" @default.
- W4205265212 created "2022-01-26" @default.
- W4205265212 creator A5004964780 @default.
- W4205265212 creator A5020604701 @default.
- W4205265212 creator A5030797713 @default.
- W4205265212 creator A5032622914 @default.
- W4205265212 creator A5063953575 @default.
- W4205265212 creator A5066918650 @default.
- W4205265212 date "2022-01-01" @default.
- W4205265212 modified "2023-10-17" @default.
- W4205265212 title "EBANet: Efficient Boundary-Aware Network for RGB-D Semantic Segmentation" @default.
- W4205265212 cites W125693051 @default.
- W4205265212 cites W1903029394 @default.
- W4205265212 cites W1905829557 @default.
- W4205265212 cites W2194775991 @default.
- W4205265212 cites W2339172515 @default.
- W4205265212 cites W2489780108 @default.
- W4205265212 cites W2560023338 @default.
- W4205265212 cites W2587989515 @default.
- W4205265212 cites W2609822318 @default.
- W4205265212 cites W2775906317 @default.
- W4205265212 cites W2777686015 @default.
- W4205265212 cites W2799166040 @default.
- W4205265212 cites W2886802132 @default.
- W4205265212 cites W2920326761 @default.
- W4205265212 cites W2922509574 @default.
- W4205265212 cites W2955058313 @default.
- W4205265212 cites W2959581809 @default.
- W4205265212 cites W2961348656 @default.
- W4205265212 cites W2962802951 @default.
- W4205265212 cites W2963091558 @default.
- W4205265212 cites W2963419596 @default.
- W4205265212 cites W2963420686 @default.
- W4205265212 cites W2963896186 @default.
- W4205265212 cites W2964121718 @default.
- W4205265212 cites W2964241181 @default.
- W4205265212 cites W2966926453 @default.
- W4205265212 cites W2971014764 @default.
- W4205265212 cites W2971290066 @default.
- W4205265212 cites W2971298073 @default.
- W4205265212 cites W2982453938 @default.
- W4205265212 cites W2985459778 @default.
- W4205265212 cites W2990032492 @default.
- W4205265212 cites W2990775046 @default.
- W4205265212 cites W2991062542 @default.
- W4205265212 cites W3034868495 @default.
- W4205265212 cites W3099155473 @default.
- W4205265212 cites W3108601100 @default.
- W4205265212 cites W3110108516 @default.
- W4205265212 cites W3124434019 @default.
- W4205265212 doi "https://doi.org/10.1007/978-981-16-9247-5_16" @default.
- W4205265212 hasPublicationYear "2022" @default.
- W4205265212 type Work @default.
- W4205265212 citedByCount "0" @default.
- W4205265212 crossrefType "book-chapter" @default.
- W4205265212 hasAuthorship W4205265212A5004964780 @default.
- W4205265212 hasAuthorship W4205265212A5020604701 @default.
- W4205265212 hasAuthorship W4205265212A5030797713 @default.
- W4205265212 hasAuthorship W4205265212A5032622914 @default.
- W4205265212 hasAuthorship W4205265212A5063953575 @default.
- W4205265212 hasAuthorship W4205265212A5066918650 @default.
- W4205265212 hasConcept C115961682 @default.
- W4205265212 hasConcept C124504099 @default.
- W4205265212 hasConcept C134306372 @default.
- W4205265212 hasConcept C146849305 @default.
- W4205265212 hasConcept C14705441 @default.
- W4205265212 hasConcept C153180895 @default.
- W4205265212 hasConcept C154945302 @default.
- W4205265212 hasConcept C160633673 @default.
- W4205265212 hasConcept C193536780 @default.
- W4205265212 hasConcept C31972630 @default.
- W4205265212 hasConcept C33923547 @default.
- W4205265212 hasConcept C41008148 @default.
- W4205265212 hasConcept C62354387 @default.
- W4205265212 hasConcept C82990744 @default.
- W4205265212 hasConcept C89600930 @default.
- W4205265212 hasConcept C9417928 @default.
- W4205265212 hasConceptScore W4205265212C115961682 @default.
- W4205265212 hasConceptScore W4205265212C124504099 @default.
- W4205265212 hasConceptScore W4205265212C134306372 @default.
- W4205265212 hasConceptScore W4205265212C146849305 @default.
- W4205265212 hasConceptScore W4205265212C14705441 @default.
- W4205265212 hasConceptScore W4205265212C153180895 @default.
- W4205265212 hasConceptScore W4205265212C154945302 @default.
- W4205265212 hasConceptScore W4205265212C160633673 @default.
- W4205265212 hasConceptScore W4205265212C193536780 @default.
- W4205265212 hasConceptScore W4205265212C31972630 @default.
- W4205265212 hasConceptScore W4205265212C33923547 @default.
- W4205265212 hasConceptScore W4205265212C41008148 @default.
- W4205265212 hasConceptScore W4205265212C62354387 @default.
- W4205265212 hasConceptScore W4205265212C82990744 @default.
- W4205265212 hasConceptScore W4205265212C89600930 @default.
- W4205265212 hasConceptScore W4205265212C9417928 @default.
- W4205265212 hasLocation W42052652121 @default.
- W4205265212 hasOpenAccess W4205265212 @default.
- W4205265212 hasPrimaryLocation W42052652121 @default.
- W4205265212 hasRelatedWork W1981132553 @default.
- W4205265212 hasRelatedWork W2100493112 @default.