Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891802093> ?p ?o ?g. }
- W2891802093 abstract "Pixel-level annotation demands expensive human efforts and limits the performance of deep networks that usually benefits from more such training data. In this work we aim to achieve high quality instance and semantic segmentation results over a small set of pixel-level mask annotations and a large set of box annotations. The basic idea is exploring detection models to simplify the pixel-level supervised learning task and thus reduce the required amount of mask annotations. Our architecture, named DASNet, consists of three modules: detection, attention, and segmentation. The detection module detects all classes of objects, the attention module generates multi-scale class-specific features, and the segmentation module recovers the binary masks. Our method demonstrates substantially improved performance compared to existing semi-supervised approaches on PASCAL VOC 2012 dataset." @default.
- W2891802093 created "2018-09-27" @default.
- W2891802093 creator A5065193592 @default.
- W2891802093 creator A5070504653 @default.
- W2891802093 creator A5091673337 @default.
- W2891802093 date "2018-09-17" @default.
- W2891802093 modified "2023-09-26" @default.
- W2891802093 title "DASNet: Reducing Pixel-level Annotations for Instance and Semantic Segmentation." @default.
- W2891802093 cites W1495267108 @default.
- W2891802093 cites W1536680647 @default.
- W2891802093 cites W1745334888 @default.
- W2891802093 cites W1783315696 @default.
- W2891802093 cites W1861492603 @default.
- W2891802093 cites W1903029394 @default.
- W2891802093 cites W1927251054 @default.
- W2891802093 cites W1945608308 @default.
- W2891802093 cites W2031489346 @default.
- W2891802093 cites W2088049833 @default.
- W2891802093 cites W2108598243 @default.
- W2891802093 cites W2124351162 @default.
- W2891802093 cites W2133515615 @default.
- W2891802093 cites W2137278143 @default.
- W2891802093 cites W2144794286 @default.
- W2891802093 cites W2155893237 @default.
- W2891802093 cites W2198291924 @default.
- W2891802093 cites W2221898772 @default.
- W2891802093 cites W2277195237 @default.
- W2891802093 cites W2291422229 @default.
- W2891802093 cites W2312198368 @default.
- W2891802093 cites W2337429362 @default.
- W2891802093 cites W2516803306 @default.
- W2891802093 cites W2552414813 @default.
- W2891802093 cites W2555182955 @default.
- W2891802093 cites W2585521554 @default.
- W2891802093 cites W2605214291 @default.
- W2891802093 cites W2738853914 @default.
- W2891802093 cites W2739450375 @default.
- W2891802093 cites W2787091153 @default.
- W2891802093 cites W2962835968 @default.
- W2891802093 cites W2962841641 @default.
- W2891802093 cites W2963881378 @default.
- W2891802093 cites W2963977581 @default.
- W2891802093 cites W2964288706 @default.
- W2891802093 cites W3106250896 @default.
- W2891802093 cites W586034241 @default.
- W2891802093 cites W611457968 @default.
- W2891802093 cites W639708223 @default.
- W2891802093 hasPublicationYear "2018" @default.
- W2891802093 type Work @default.
- W2891802093 sameAs 2891802093 @default.
- W2891802093 citedByCount "0" @default.
- W2891802093 crossrefType "posted-content" @default.
- W2891802093 hasAuthorship W2891802093A5065193592 @default.
- W2891802093 hasAuthorship W2891802093A5070504653 @default.
- W2891802093 hasAuthorship W2891802093A5091673337 @default.
- W2891802093 hasConcept C119857082 @default.
- W2891802093 hasConcept C153180895 @default.
- W2891802093 hasConcept C154945302 @default.
- W2891802093 hasConcept C160633673 @default.
- W2891802093 hasConcept C177264268 @default.
- W2891802093 hasConcept C199360897 @default.
- W2891802093 hasConcept C2776145971 @default.
- W2891802093 hasConcept C2776321320 @default.
- W2891802093 hasConcept C41008148 @default.
- W2891802093 hasConcept C51632099 @default.
- W2891802093 hasConcept C75608658 @default.
- W2891802093 hasConcept C89600930 @default.
- W2891802093 hasConceptScore W2891802093C119857082 @default.
- W2891802093 hasConceptScore W2891802093C153180895 @default.
- W2891802093 hasConceptScore W2891802093C154945302 @default.
- W2891802093 hasConceptScore W2891802093C160633673 @default.
- W2891802093 hasConceptScore W2891802093C177264268 @default.
- W2891802093 hasConceptScore W2891802093C199360897 @default.
- W2891802093 hasConceptScore W2891802093C2776145971 @default.
- W2891802093 hasConceptScore W2891802093C2776321320 @default.
- W2891802093 hasConceptScore W2891802093C41008148 @default.
- W2891802093 hasConceptScore W2891802093C51632099 @default.
- W2891802093 hasConceptScore W2891802093C75608658 @default.
- W2891802093 hasConceptScore W2891802093C89600930 @default.
- W2891802093 hasLocation W28918020931 @default.
- W2891802093 hasOpenAccess W2891802093 @default.
- W2891802093 hasPrimaryLocation W28918020931 @default.
- W2891802093 hasRelatedWork W2585521554 @default.
- W2891802093 hasRelatedWork W2768923469 @default.
- W2891802093 hasRelatedWork W2798683932 @default.
- W2891802093 hasRelatedWork W2800060851 @default.
- W2891802093 hasRelatedWork W2887681327 @default.
- W2891802093 hasRelatedWork W2902978875 @default.
- W2891802093 hasRelatedWork W2904397670 @default.
- W2891802093 hasRelatedWork W2907775992 @default.
- W2891802093 hasRelatedWork W2928569631 @default.
- W2891802093 hasRelatedWork W2964248460 @default.
- W2891802093 hasRelatedWork W2966776792 @default.
- W2891802093 hasRelatedWork W3011874042 @default.
- W2891802093 hasRelatedWork W3105043467 @default.
- W2891802093 hasRelatedWork W3106029750 @default.
- W2891802093 hasRelatedWork W3108636759 @default.
- W2891802093 hasRelatedWork W3108678367 @default.
- W2891802093 hasRelatedWork W3119507534 @default.
- W2891802093 hasRelatedWork W3121791778 @default.