FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3126152110> ?p ?o ?g. }

• W3126152110 abstract "Existing CNNs-Based RGB-D Salient Object Detection (SOD) networks are all required to be pre-trained on the ImageNet to learn the hierarchy features which can help to provide a good initialization. However, the collection and annotation of large-scale datasets are time-consuming and expensive. In this paper, we utilize Self-Supervised Representation Learning (SSL) to design two pretext tasks: the cross-modal auto-encoder and the depth-contour estimation. Our pretext tasks require only a few and unlabeled RGB-D datasets to perform pre-training, which makes the network capture rich semantic contexts and reduce the gap between two modalities, thereby providing an effective initialization for the downstream task. In addition, for the inherent problem of cross-modal fusion in RGB-D SOD, we propose a consistency-difference aggregation (CDA) module that splits a single feature fusion into multi-path fusion to achieve an adequate perception of consistent and differential information. The CDA module is general and suitable for both cross-modal and cross-level feature fusion. Extensive experiments on six benchmark RGB-D SOD datasets, our model pre-trained on the RGB-D dataset ($6,392$ without any annotations) can perform favorably against most state-of-the-art RGB-D methods pre-trained on ImageNet ($1,280,000$ with image-level annotations)." @default.
• W3126152110 created "2021-02-15" @default.
• W3126152110 creator A5006986293 @default.
• W3126152110 creator A5015500789 @default.
• W3126152110 creator A5015967560 @default.
• W3126152110 creator A5040300820 @default.
• W3126152110 creator A5050583798 @default.
• W3126152110 date "2021-01-29" @default.
• W3126152110 modified "2023-09-27" @default.
• W3126152110 title "Self-Supervised Representation Learning for RGB-D Salient Object Detection." @default.
• W3126152110 cites W1520997877 @default.
• W3126152110 cites W1580389772 @default.
• W3126152110 cites W1686810756 @default.
• W3126152110 cites W1817277359 @default.
• W3126152110 cites W1966025376 @default.
• W3126152110 cites W1986670485 @default.
• W3126152110 cites W1993713494 @default.
• W3126152110 cites W1994922096 @default.
• W3126152110 cites W2002781701 @default.
• W3126152110 cites W2039313011 @default.
• W3126152110 cites W20683899 @default.
• W3126152110 cites W2086791339 @default.
• W3126152110 cites W2100470808 @default.
• W3126152110 cites W2108598243 @default.
• W3126152110 cites W2113687551 @default.
• W3126152110 cites W2117130368 @default.
• W3126152110 cites W2130903752 @default.
• W3126152110 cites W2132083787 @default.
• W3126152110 cites W2153579005 @default.
• W3126152110 cites W219040644 @default.
• W3126152110 cites W2461758788 @default.
• W3126152110 cites W2487442924 @default.
• W3126152110 cites W2565639579 @default.
• W3126152110 cites W2599837529 @default.
• W3126152110 cites W2620958690 @default.
• W3126152110 cites W2740667773 @default.
• W3126152110 cites W2765838470 @default.
• W3126152110 cites W2798791651 @default.
• W3126152110 cites W2798857366 @default.
• W3126152110 cites W2799074129 @default.
• W3126152110 cites W2804610335 @default.
• W3126152110 cites W2883725317 @default.
• W3126152110 cites W2887522866 @default.
• W3126152110 cites W2907643346 @default.
• W3126152110 cites W2909381593 @default.
• W3126152110 cites W2937549930 @default.
• W3126152110 cites W2948300571 @default.
• W3126152110 cites W2948500402 @default.
• W3126152110 cites W2950622378 @default.
• W3126152110 cites W2957414648 @default.
• W3126152110 cites W2962159375 @default.
• W3126152110 cites W2963420272 @default.
• W3126152110 cites W2963868681 @default.
• W3126152110 cites W2964048159 @default.
• W3126152110 cites W2990873191 @default.
• W3126152110 cites W3002301267 @default.
• W3126152110 cites W3010616503 @default.
• W3126152110 cites W3034320133 @default.
• W3126152110 cites W3035284915 @default.
• W3126152110 cites W3035290198 @default.
• W3126152110 cites W3035357085 @default.
• W3126152110 cites W3035422681 @default.
• W3126152110 cites W3035633116 @default.
• W3126152110 cites W3097053213 @default.
• W3126152110 cites W3106587394 @default.
• W3126152110 cites W3107944836 @default.
• W3126152110 cites W3108421143 @default.
• W3126152110 cites W3108812909 @default.
• W3126152110 cites W3108822985 @default.
• W3126152110 cites W3114152269 @default.
• W3126152110 cites W3114738484 @default.
• W3126152110 cites W343636949 @default.
• W3126152110 hasPublicationYear "2021" @default.
• W3126152110 type Work @default.
• W3126152110 sameAs 3126152110 @default.
• W3126152110 citedByCount "0" @default.
• W3126152110 crossrefType "posted-content" @default.
• W3126152110 hasAuthorship W3126152110A5006986293 @default.
• W3126152110 hasAuthorship W3126152110A5015500789 @default.
• W3126152110 hasAuthorship W3126152110A5015967560 @default.
• W3126152110 hasAuthorship W3126152110A5040300820 @default.
• W3126152110 hasAuthorship W3126152110A5050583798 @default.
• W3126152110 hasConcept C114466953 @default.
• W3126152110 hasConcept C119857082 @default.
• W3126152110 hasConcept C13280743 @default.
• W3126152110 hasConcept C138885662 @default.
• W3126152110 hasConcept C153180895 @default.
• W3126152110 hasConcept C154945302 @default.
• W3126152110 hasConcept C185798385 @default.
• W3126152110 hasConcept C199360897 @default.
• W3126152110 hasConcept C205649164 @default.
• W3126152110 hasConcept C2776321320 @default.
• W3126152110 hasConcept C2776401178 @default.
• W3126152110 hasConcept C31972630 @default.
• W3126152110 hasConcept C41008148 @default.
• W3126152110 hasConcept C41895202 @default.
• W3126152110 hasConcept C59404180 @default.
• W3126152110 hasConcept C63584917 @default.
• W3126152110 hasConcept C82990744 @default.
• W3126152110 hasConceptScore W3126152110C114466953 @default.

• next