FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312585350> ?p ?o ?g. }

• W4312585350 endingPage "476" @default.
• W4312585350 startingPage "459" @default.
• W4312585350 abstract "We propose a test-time adaptation method for cross-domain image segmentation. Our method is simple: Given a new unseen instance at test time, we adapt a pre-trained model by conducting instance-specific BatchNorm (statistics) calibration. Our approach has two core components. First, we replace the manually designed BatchNorm calibration rule with a learnable module. Second, we leverage strong data augmentation to simulate random domain shifts for learning the calibration rule. In contrast to existing domain adaptation methods, our method does not require accessing the target domain data at training time or conducting computationally expensive test-time model training/optimization. Equipping our method with models trained by standard recipes achieves significant improvement, comparing favorably with several state-of-the-art domain generalization and one-shot unsupervised domain adaptation approaches. Combining our method with the domain generalization methods further improves performance, reaching a new state of the art. Our project page is https://yuliang.vision/InstCal/ ." @default.
• W4312585350 created "2023-01-05" @default.
• W4312585350 creator A5024743253 @default.
• W4312585350 creator A5025631228 @default.
• W4312585350 creator A5042346519 @default.
• W4312585350 creator A5050852420 @default.
• W4312585350 creator A5053730462 @default.
• W4312585350 creator A5075054918 @default.
• W4312585350 date "2022-01-01" @default.
• W4312585350 modified "2023-09-26" @default.
• W4312585350 title "Learning Instance-Specific Adaptation for Cross-Domain Segmentation" @default.
• W4312585350 cites W2104094955 @default.
• W4312585350 cites W2340897893 @default.
• W4312585350 cites W2431874326 @default.
• W4312585350 cites W2487365028 @default.
• W4312585350 cites W2584009249 @default.
• W4312585350 cites W2593768305 @default.
• W4312585350 cites W2748021867 @default.
• W4312585350 cites W2781228439 @default.
• W4312585350 cites W2793888044 @default.
• W4312585350 cites W2883780447 @default.
• W4312585350 cites W2884366600 @default.
• W4312585350 cites W2894903065 @default.
• W4312585350 cites W2895281799 @default.
• W4312585350 cites W2950111065 @default.
• W4312585350 cites W2962793481 @default.
• W4312585350 cites W2963073217 @default.
• W4312585350 cites W2963163009 @default.
• W4312585350 cites W2963709863 @default.
• W4312585350 cites W2964288524 @default.
• W4312585350 cites W2969893028 @default.
• W4312585350 cites W2979475574 @default.
• W4312585350 cites W2981368934 @default.
• W4312585350 cites W2981488580 @default.
• W4312585350 cites W2981512393 @default.
• W4312585350 cites W2985406498 @default.
• W4312585350 cites W2998653622 @default.
• W4312585350 cites W2999219213 @default.
• W4312585350 cites W3034355852 @default.
• W4312585350 cites W3034373371 @default.
• W4312585350 cites W3035564946 @default.
• W4312585350 cites W3035682985 @default.
• W4312585350 cites W3037492894 @default.
• W4312585350 cites W3169545167 @default.
• W4312585350 cites W3172854222 @default.
• W4312585350 cites W3179539006 @default.
• W4312585350 cites W3215113235 @default.
• W4312585350 doi "https://doi.org/10.1007/978-3-031-19827-4_27" @default.
• W4312585350 hasPublicationYear "2022" @default.
• W4312585350 type Work @default.
• W4312585350 citedByCount "1" @default.
• W4312585350 countsByYear W43125853502023 @default.
• W4312585350 crossrefType "book-chapter" @default.
• W4312585350 hasAuthorship W4312585350A5024743253 @default.
• W4312585350 hasAuthorship W4312585350A5025631228 @default.
• W4312585350 hasAuthorship W4312585350A5042346519 @default.
• W4312585350 hasAuthorship W4312585350A5050852420 @default.
• W4312585350 hasAuthorship W4312585350A5053730462 @default.
• W4312585350 hasAuthorship W4312585350A5075054918 @default.
• W4312585350 hasBestOaLocation W43125853502 @default.
• W4312585350 hasConcept C105795698 @default.
• W4312585350 hasConcept C119857082 @default.
• W4312585350 hasConcept C120665830 @default.
• W4312585350 hasConcept C121332964 @default.
• W4312585350 hasConcept C134306372 @default.
• W4312585350 hasConcept C139807058 @default.
• W4312585350 hasConcept C153083717 @default.
• W4312585350 hasConcept C153180895 @default.
• W4312585350 hasConcept C154945302 @default.
• W4312585350 hasConcept C165838908 @default.
• W4312585350 hasConcept C16910744 @default.
• W4312585350 hasConcept C177148314 @default.
• W4312585350 hasConcept C199360897 @default.
• W4312585350 hasConcept C2776434776 @default.
• W4312585350 hasConcept C33923547 @default.
• W4312585350 hasConcept C36503486 @default.
• W4312585350 hasConcept C41008148 @default.
• W4312585350 hasConcept C89600930 @default.
• W4312585350 hasConcept C95623464 @default.
• W4312585350 hasConceptScore W4312585350C105795698 @default.
• W4312585350 hasConceptScore W4312585350C119857082 @default.
• W4312585350 hasConceptScore W4312585350C120665830 @default.
• W4312585350 hasConceptScore W4312585350C121332964 @default.
• W4312585350 hasConceptScore W4312585350C134306372 @default.
• W4312585350 hasConceptScore W4312585350C139807058 @default.
• W4312585350 hasConceptScore W4312585350C153083717 @default.
• W4312585350 hasConceptScore W4312585350C153180895 @default.
• W4312585350 hasConceptScore W4312585350C154945302 @default.
• W4312585350 hasConceptScore W4312585350C165838908 @default.
• W4312585350 hasConceptScore W4312585350C16910744 @default.
• W4312585350 hasConceptScore W4312585350C177148314 @default.
• W4312585350 hasConceptScore W4312585350C199360897 @default.
• W4312585350 hasConceptScore W4312585350C2776434776 @default.
• W4312585350 hasConceptScore W4312585350C33923547 @default.
• W4312585350 hasConceptScore W4312585350C36503486 @default.
• W4312585350 hasConceptScore W4312585350C41008148 @default.
• W4312585350 hasConceptScore W4312585350C89600930 @default.
• W4312585350 hasConceptScore W4312585350C95623464 @default.

• next