Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204507850> ?p ?o ?g. }
- W3204507850 abstract "Weakly supervised instance segmentation (WSIS) with only image-level labels has recently drawn much attention. To date, bottom-up WSIS methods refine discriminative cues from classifiers with sophisticated multi-stage training procedures, which also suffer from inconsistent object boundaries. And top-down WSIS methods are formulated as cascade detection-to-segmentation pipeline, in which the quality of segmentation learning heavily depends on pseudo masks generated from detectors. In this paper, we propose a unified parallel detection-and-segmentation learning (PDSL) framework to learn instance segmentation with only image-level labels, which draws inspiration from both top-down and bottom-up instance segmentation approaches. The detection module is the same as the typical design of any weakly supervised object detection, while the segmentation module leverages self-supervised learning to model class-agnostic foreground extraction, following by self-training to refine class-specific segmentation. We further design instance-activation correlation module to improve the coherence between detection and segmentation branches. Extensive experiments verify that the proposed method outperforms baselines and achieves the state-of-the-art results on PASCAL VOC and MS COCO." @default.
- W3204507850 created "2021-10-11" @default.
- W3204507850 creator A5012409526 @default.
- W3204507850 creator A5014628588 @default.
- W3204507850 creator A5015525872 @default.
- W3204507850 creator A5016080094 @default.
- W3204507850 creator A5039883116 @default.
- W3204507850 creator A5057324666 @default.
- W3204507850 creator A5067413001 @default.
- W3204507850 creator A5077357809 @default.
- W3204507850 date "2021-10-01" @default.
- W3204507850 modified "2023-10-12" @default.
- W3204507850 title "Parallel Detection-and-Segmentation Learning for Weakly Supervised Instance Segmentation" @default.
- W3204507850 cites W1507506748 @default.
- W3204507850 cites W1536680647 @default.
- W3204507850 cites W1934621328 @default.
- W3204507850 cites W1991367009 @default.
- W3204507850 cites W2010792435 @default.
- W3204507850 cites W2016016818 @default.
- W3204507850 cites W2031489346 @default.
- W3204507850 cites W2088049833 @default.
- W3204507850 cites W2108598243 @default.
- W3204507850 cites W2194775991 @default.
- W3204507850 cites W2220111505 @default.
- W3204507850 cites W2295107390 @default.
- W3204507850 cites W2340897893 @default.
- W3204507850 cites W2441255125 @default.
- W3204507850 cites W2503388974 @default.
- W3204507850 cites W2519284461 @default.
- W3204507850 cites W2552414813 @default.
- W3204507850 cites W2604260814 @default.
- W3204507850 cites W2606831796 @default.
- W3204507850 cites W2613833277 @default.
- W3204507850 cites W2797826601 @default.
- W3204507850 cites W2798748179 @default.
- W3204507850 cites W2799177530 @default.
- W3204507850 cites W2886773299 @default.
- W3204507850 cites W2894666165 @default.
- W3204507850 cites W2904026127 @default.
- W3204507850 cites W2953433552 @default.
- W3204507850 cites W2954087924 @default.
- W3204507850 cites W2955278847 @default.
- W3204507850 cites W2962758679 @default.
- W3204507850 cites W2962867364 @default.
- W3204507850 cites W2963150697 @default.
- W3204507850 cites W2963311325 @default.
- W3204507850 cites W2963603913 @default.
- W3204507850 cites W2963795442 @default.
- W3204507850 cites W2963949812 @default.
- W3204507850 cites W2963952323 @default.
- W3204507850 cites W2964328846 @default.
- W3204507850 cites W2983061571 @default.
- W3204507850 cites W2990400263 @default.
- W3204507850 cites W2991023920 @default.
- W3204507850 cites W2994041372 @default.
- W3204507850 cites W2997079108 @default.
- W3204507850 cites W2997125355 @default.
- W3204507850 cites W3017351200 @default.
- W3204507850 cites W3034329658 @default.
- W3204507850 cites W3035271324 @default.
- W3204507850 cites W3035703639 @default.
- W3204507850 cites W3035725370 @default.
- W3204507850 cites W3046582853 @default.
- W3204507850 cites W3093397049 @default.
- W3204507850 cites W3095191037 @default.
- W3204507850 cites W3109073404 @default.
- W3204507850 cites W3170130651 @default.
- W3204507850 cites W318792885 @default.
- W3204507850 cites W4248635988 @default.
- W3204507850 cites W4250589301 @default.
- W3204507850 doi "https://doi.org/10.1109/iccv48922.2021.00809" @default.
- W3204507850 hasPublicationYear "2021" @default.
- W3204507850 type Work @default.
- W3204507850 sameAs 3204507850 @default.
- W3204507850 citedByCount "5" @default.
- W3204507850 countsByYear W32045078502022 @default.
- W3204507850 countsByYear W32045078502023 @default.
- W3204507850 crossrefType "proceedings-article" @default.
- W3204507850 hasAuthorship W3204507850A5012409526 @default.
- W3204507850 hasAuthorship W3204507850A5014628588 @default.
- W3204507850 hasAuthorship W3204507850A5015525872 @default.
- W3204507850 hasAuthorship W3204507850A5016080094 @default.
- W3204507850 hasAuthorship W3204507850A5039883116 @default.
- W3204507850 hasAuthorship W3204507850A5057324666 @default.
- W3204507850 hasAuthorship W3204507850A5067413001 @default.
- W3204507850 hasAuthorship W3204507850A5077357809 @default.
- W3204507850 hasConcept C119857082 @default.
- W3204507850 hasConcept C124504099 @default.
- W3204507850 hasConcept C136389625 @default.
- W3204507850 hasConcept C153180895 @default.
- W3204507850 hasConcept C154945302 @default.
- W3204507850 hasConcept C199360897 @default.
- W3204507850 hasConcept C25694479 @default.
- W3204507850 hasConcept C2776151529 @default.
- W3204507850 hasConcept C31972630 @default.
- W3204507850 hasConcept C41008148 @default.
- W3204507850 hasConcept C50644808 @default.
- W3204507850 hasConcept C65885262 @default.
- W3204507850 hasConcept C75608658 @default.
- W3204507850 hasConcept C89600930 @default.