Matches in SemOpenAlex for { <https://semopenalex.org/work/W3026372364> ?p ?o ?g. }
- W3026372364 abstract "Instance segmentation of unknown objects from images is regarded as relevant for several robot skills including grasping, tracking and object sorting. Recent results in computer vision have shown that large hand-labeled datasets enable high segmentation performance. To overcome the time-consuming process of manually labeling data for new environments, we present a transfer learning approach for robots that learn to segment objects by interacting with their environment in a self-supervised manner. Our robot pushes unknown objects on a table and uses information from optical flow to create training labels in the form of object masks. To achieve this, we fine-tune an existing DeepMask network for instance segmentation on the self-labeled training data acquired by the robot. We evaluate our trained network (SelfDeepMask) on a set of real images showing challenging and cluttered scenes with novel objects. Here, SelfDeepMask outperforms the DeepMask network trained on the COCO dataset by 9.5% in average precision. Furthermore, we combine our approach with recent approaches for training with noisy labels in order to better cope with induced label noise." @default.
- W3026372364 created "2020-05-29" @default.
- W3026372364 creator A5064393022 @default.
- W3026372364 creator A5078164142 @default.
- W3026372364 creator A5084499878 @default.
- W3026372364 date "2020-05-19" @default.
- W3026372364 modified "2023-09-25" @default.
- W3026372364 title "Self-supervised Transfer Learning for Instance Segmentation through Physical Interaction" @default.
- W3026372364 cites W1594098193 @default.
- W3026372364 cites W1861492603 @default.
- W3026372364 cites W1972630525 @default.
- W3026372364 cites W1980076217 @default.
- W3026372364 cites W2041108426 @default.
- W3026372364 cites W2088076141 @default.
- W3026372364 cites W2093334045 @default.
- W3026372364 cites W2101128524 @default.
- W3026372364 cites W2110762409 @default.
- W3026372364 cites W2121947440 @default.
- W3026372364 cites W2132984949 @default.
- W3026372364 cites W2152425170 @default.
- W3026372364 cites W2165830610 @default.
- W3026372364 cites W2201912979 @default.
- W3026372364 cites W2322480645 @default.
- W3026372364 cites W2340935928 @default.
- W3026372364 cites W2558625610 @default.
- W3026372364 cites W2560474170 @default.
- W3026372364 cites W2575671312 @default.
- W3026372364 cites W2600030077 @default.
- W3026372364 cites W2604662268 @default.
- W3026372364 cites W2736480544 @default.
- W3026372364 cites W2769112066 @default.
- W3026372364 cites W2779985940 @default.
- W3026372364 cites W2807314955 @default.
- W3026372364 cites W2908549092 @default.
- W3026372364 cites W2913921102 @default.
- W3026372364 cites W2962736495 @default.
- W3026372364 cites W2962762541 @default.
- W3026372364 cites W2962791145 @default.
- W3026372364 cites W2962793652 @default.
- W3026372364 cites W2962976158 @default.
- W3026372364 cites W2963244312 @default.
- W3026372364 cites W2963462012 @default.
- W3026372364 cites W2963678509 @default.
- W3026372364 cites W2963735582 @default.
- W3026372364 cites W2963826370 @default.
- W3026372364 cites W2964052394 @default.
- W3026372364 cites W2964112890 @default.
- W3026372364 cites W2966885779 @default.
- W3026372364 cites W3021544315 @default.
- W3026372364 cites W3105287169 @default.
- W3026372364 cites W809122546 @default.
- W3026372364 hasPublicationYear "2020" @default.
- W3026372364 type Work @default.
- W3026372364 sameAs 3026372364 @default.
- W3026372364 citedByCount "0" @default.
- W3026372364 crossrefType "posted-content" @default.
- W3026372364 hasAuthorship W3026372364A5064393022 @default.
- W3026372364 hasAuthorship W3026372364A5078164142 @default.
- W3026372364 hasAuthorship W3026372364A5084499878 @default.
- W3026372364 hasConcept C111696304 @default.
- W3026372364 hasConcept C111919701 @default.
- W3026372364 hasConcept C115961682 @default.
- W3026372364 hasConcept C119857082 @default.
- W3026372364 hasConcept C150899416 @default.
- W3026372364 hasConcept C153180895 @default.
- W3026372364 hasConcept C154945302 @default.
- W3026372364 hasConcept C177264268 @default.
- W3026372364 hasConcept C199360897 @default.
- W3026372364 hasConcept C2781238097 @default.
- W3026372364 hasConcept C31972630 @default.
- W3026372364 hasConcept C41008148 @default.
- W3026372364 hasConcept C89600930 @default.
- W3026372364 hasConcept C90509273 @default.
- W3026372364 hasConcept C98045186 @default.
- W3026372364 hasConcept C99498987 @default.
- W3026372364 hasConceptScore W3026372364C111696304 @default.
- W3026372364 hasConceptScore W3026372364C111919701 @default.
- W3026372364 hasConceptScore W3026372364C115961682 @default.
- W3026372364 hasConceptScore W3026372364C119857082 @default.
- W3026372364 hasConceptScore W3026372364C150899416 @default.
- W3026372364 hasConceptScore W3026372364C153180895 @default.
- W3026372364 hasConceptScore W3026372364C154945302 @default.
- W3026372364 hasConceptScore W3026372364C177264268 @default.
- W3026372364 hasConceptScore W3026372364C199360897 @default.
- W3026372364 hasConceptScore W3026372364C2781238097 @default.
- W3026372364 hasConceptScore W3026372364C31972630 @default.
- W3026372364 hasConceptScore W3026372364C41008148 @default.
- W3026372364 hasConceptScore W3026372364C89600930 @default.
- W3026372364 hasConceptScore W3026372364C90509273 @default.
- W3026372364 hasConceptScore W3026372364C98045186 @default.
- W3026372364 hasConceptScore W3026372364C99498987 @default.
- W3026372364 hasLocation W30263723641 @default.
- W3026372364 hasOpenAccess W3026372364 @default.
- W3026372364 hasPrimaryLocation W30263723641 @default.
- W3026372364 hasRelatedWork W2045184456 @default.
- W3026372364 hasRelatedWork W2755686789 @default.
- W3026372364 hasRelatedWork W2901412525 @default.
- W3026372364 hasRelatedWork W2905120940 @default.
- W3026372364 hasRelatedWork W2906686884 @default.
- W3026372364 hasRelatedWork W2914143419 @default.