Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313142172> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W4313142172 endingPage "299" @default.
- W4313142172 startingPage "283" @default.
- W4313142172 abstract "A significant bottleneck in training deep networks for part segmentation is the cost of obtaining detailed annotations. We propose a framework to exploit coarse labels such as figure-ground masks and keypoint locations that are readily available for some categories to improve part segmentation models. A key challenge is that these annotations were collected for different tasks and with different labeling styles and cannot be readily mapped to the part labels. To this end, we propose to jointly learn the dependencies between labeling styles and the part segmentation model, allowing us to utilize supervision from diverse labels. To evaluate our approach we develop a benchmark on the Caltech-UCSD birds and OID Aircraft dataset. Our approach outperforms baselines based on multi-task learning, semi-supervised learning, and competitive methods relying on loss functions manually designed to exploit coarse supervision." @default.
- W4313142172 created "2023-01-06" @default.
- W4313142172 creator A5036639026 @default.
- W4313142172 creator A5052551454 @default.
- W4313142172 creator A5067219074 @default.
- W4313142172 date "2022-01-01" @default.
- W4313142172 modified "2023-10-17" @default.
- W4313142172 title "Improving Few-Shot Part Segmentation Using Coarse Supervision" @default.
- W4313142172 cites W1954152232 @default.
- W4313142172 cites W2031489346 @default.
- W4313142172 cites W2079125479 @default.
- W4313142172 cites W2104408738 @default.
- W4313142172 cites W2117539524 @default.
- W4313142172 cites W2124351162 @default.
- W4313142172 cites W2216125271 @default.
- W4313142172 cites W2337429362 @default.
- W4313142172 cites W2552414813 @default.
- W4313142172 cites W2819476901 @default.
- W4313142172 cites W2955278847 @default.
- W4313142172 cites W2962784289 @default.
- W4313142172 cites W2962867364 @default.
- W4313142172 cites W2963150697 @default.
- W4313142172 cites W2963311325 @default.
- W4313142172 cites W3034930876 @default.
- W4313142172 cites W3091093964 @default.
- W4313142172 cites W3120627776 @default.
- W4313142172 cites W3167788848 @default.
- W4313142172 cites W3171581326 @default.
- W4313142172 cites W3173143063 @default.
- W4313142172 cites W3180169285 @default.
- W4313142172 cites W3209925794 @default.
- W4313142172 cites W3214773516 @default.
- W4313142172 cites W4206848004 @default.
- W4313142172 cites W4312322023 @default.
- W4313142172 doi "https://doi.org/10.1007/978-3-031-20056-4_17" @default.
- W4313142172 hasPublicationYear "2022" @default.
- W4313142172 type Work @default.
- W4313142172 citedByCount "1" @default.
- W4313142172 countsByYear W43131421722023 @default.
- W4313142172 crossrefType "book-chapter" @default.
- W4313142172 hasAuthorship W4313142172A5036639026 @default.
- W4313142172 hasAuthorship W4313142172A5052551454 @default.
- W4313142172 hasAuthorship W4313142172A5067219074 @default.
- W4313142172 hasBestOaLocation W43131421722 @default.
- W4313142172 hasConcept C108583219 @default.
- W4313142172 hasConcept C119857082 @default.
- W4313142172 hasConcept C13280743 @default.
- W4313142172 hasConcept C149635348 @default.
- W4313142172 hasConcept C154945302 @default.
- W4313142172 hasConcept C162324750 @default.
- W4313142172 hasConcept C165696696 @default.
- W4313142172 hasConcept C185798385 @default.
- W4313142172 hasConcept C187736073 @default.
- W4313142172 hasConcept C205649164 @default.
- W4313142172 hasConcept C26517878 @default.
- W4313142172 hasConcept C2780451532 @default.
- W4313142172 hasConcept C2780513914 @default.
- W4313142172 hasConcept C38652104 @default.
- W4313142172 hasConcept C41008148 @default.
- W4313142172 hasConcept C89600930 @default.
- W4313142172 hasConceptScore W4313142172C108583219 @default.
- W4313142172 hasConceptScore W4313142172C119857082 @default.
- W4313142172 hasConceptScore W4313142172C13280743 @default.
- W4313142172 hasConceptScore W4313142172C149635348 @default.
- W4313142172 hasConceptScore W4313142172C154945302 @default.
- W4313142172 hasConceptScore W4313142172C162324750 @default.
- W4313142172 hasConceptScore W4313142172C165696696 @default.
- W4313142172 hasConceptScore W4313142172C185798385 @default.
- W4313142172 hasConceptScore W4313142172C187736073 @default.
- W4313142172 hasConceptScore W4313142172C205649164 @default.
- W4313142172 hasConceptScore W4313142172C26517878 @default.
- W4313142172 hasConceptScore W4313142172C2780451532 @default.
- W4313142172 hasConceptScore W4313142172C2780513914 @default.
- W4313142172 hasConceptScore W4313142172C38652104 @default.
- W4313142172 hasConceptScore W4313142172C41008148 @default.
- W4313142172 hasConceptScore W4313142172C89600930 @default.
- W4313142172 hasLocation W43131421721 @default.
- W4313142172 hasLocation W43131421722 @default.
- W4313142172 hasOpenAccess W4313142172 @default.
- W4313142172 hasPrimaryLocation W43131421721 @default.
- W4313142172 hasRelatedWork W2790662084 @default.
- W4313142172 hasRelatedWork W2948658236 @default.
- W4313142172 hasRelatedWork W4223527717 @default.
- W4313142172 hasRelatedWork W4223943233 @default.
- W4313142172 hasRelatedWork W4293211451 @default.
- W4313142172 hasRelatedWork W4309045103 @default.
- W4313142172 hasRelatedWork W4312200629 @default.
- W4313142172 hasRelatedWork W4313142172 @default.
- W4313142172 hasRelatedWork W4360585206 @default.
- W4313142172 hasRelatedWork W4364306694 @default.
- W4313142172 isParatext "false" @default.
- W4313142172 isRetracted "false" @default.
- W4313142172 workType "book-chapter" @default.