Matches in SemOpenAlex for { <https://semopenalex.org/work/W4290943605> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4290943605 abstract "Successful machine learning typically relies on fixed data distribution. However, due to unforeseen situations in the open world, distribution shift often occurs in applications. For instance, in the image recognition task, an unpredictable distributional shift may occur due to changes in background or lighting. Furthermore, to alleviate the harm of distribution shift, the resource budget is not infinite and often constrained. To cope with such a novel problem Resource Constrained Adaptation under Unknown Shift, in this paper we study active model adaptation both theoretically and empirically. First, we present a generalization analysis of active model adaptation for distribution shift. In theory, we show that active model adaptation could improve the generalization error from O(1/N) to O(1/N), with only a few queried samples. Second, based on the theoretical analysis, we present a systemic solution Auto, consisting of three sub-steps, that is, distribution tracking, sample selection and model adaptation. Specifically, we design a shifted distribution detection module to locate the distributional shifted samples. To fit the labeling budget, we employ a core-set algorithm to enhance the informativeness of the selected samples. Finally, we update the model through the newly queried labeled data. We conduct empirical studies of nine existing active strategies on diverse real world data sets and the results show that Auto could remarkably outperform all the baselines." @default.
- W4290943605 created "2022-08-13" @default.
- W4290943605 creator A5011185036 @default.
- W4290943605 creator A5023104005 @default.
- W4290943605 creator A5054244337 @default.
- W4290943605 creator A5087294333 @default.
- W4290943605 date "2022-08-14" @default.
- W4290943605 modified "2023-10-16" @default.
- W4290943605 title "Active Model Adaptation Under Unknown Shift" @default.
- W4290943605 cites W2593768305 @default.
- W4290943605 cites W2627183927 @default.
- W4290943605 cites W2962687275 @default.
- W4290943605 cites W2962708723 @default.
- W4290943605 cites W2963978428 @default.
- W4290943605 cites W3174493137 @default.
- W4290943605 cites W3182214289 @default.
- W4290943605 cites W3202165894 @default.
- W4290943605 doi "https://doi.org/10.1145/3534678.3539262" @default.
- W4290943605 hasPublicationYear "2022" @default.
- W4290943605 type Work @default.
- W4290943605 citedByCount "0" @default.
- W4290943605 crossrefType "proceedings-article" @default.
- W4290943605 hasAuthorship W4290943605A5011185036 @default.
- W4290943605 hasAuthorship W4290943605A5023104005 @default.
- W4290943605 hasAuthorship W4290943605A5054244337 @default.
- W4290943605 hasAuthorship W4290943605A5087294333 @default.
- W4290943605 hasConcept C110121322 @default.
- W4290943605 hasConcept C119857082 @default.
- W4290943605 hasConcept C120665830 @default.
- W4290943605 hasConcept C121332964 @default.
- W4290943605 hasConcept C124101348 @default.
- W4290943605 hasConcept C134306372 @default.
- W4290943605 hasConcept C139807058 @default.
- W4290943605 hasConcept C154945302 @default.
- W4290943605 hasConcept C177148314 @default.
- W4290943605 hasConcept C177264268 @default.
- W4290943605 hasConcept C185592680 @default.
- W4290943605 hasConcept C198531522 @default.
- W4290943605 hasConcept C199360897 @default.
- W4290943605 hasConcept C206345919 @default.
- W4290943605 hasConcept C31258907 @default.
- W4290943605 hasConcept C33923547 @default.
- W4290943605 hasConcept C41008148 @default.
- W4290943605 hasConcept C43617362 @default.
- W4290943605 hasConcept C93959086 @default.
- W4290943605 hasConceptScore W4290943605C110121322 @default.
- W4290943605 hasConceptScore W4290943605C119857082 @default.
- W4290943605 hasConceptScore W4290943605C120665830 @default.
- W4290943605 hasConceptScore W4290943605C121332964 @default.
- W4290943605 hasConceptScore W4290943605C124101348 @default.
- W4290943605 hasConceptScore W4290943605C134306372 @default.
- W4290943605 hasConceptScore W4290943605C139807058 @default.
- W4290943605 hasConceptScore W4290943605C154945302 @default.
- W4290943605 hasConceptScore W4290943605C177148314 @default.
- W4290943605 hasConceptScore W4290943605C177264268 @default.
- W4290943605 hasConceptScore W4290943605C185592680 @default.
- W4290943605 hasConceptScore W4290943605C198531522 @default.
- W4290943605 hasConceptScore W4290943605C199360897 @default.
- W4290943605 hasConceptScore W4290943605C206345919 @default.
- W4290943605 hasConceptScore W4290943605C31258907 @default.
- W4290943605 hasConceptScore W4290943605C33923547 @default.
- W4290943605 hasConceptScore W4290943605C41008148 @default.
- W4290943605 hasConceptScore W4290943605C43617362 @default.
- W4290943605 hasConceptScore W4290943605C93959086 @default.
- W4290943605 hasLocation W42909436051 @default.
- W4290943605 hasOpenAccess W4290943605 @default.
- W4290943605 hasPrimaryLocation W42909436051 @default.
- W4290943605 hasRelatedWork W1522515376 @default.
- W4290943605 hasRelatedWork W189527659 @default.
- W4290943605 hasRelatedWork W2076610045 @default.
- W4290943605 hasRelatedWork W2135470563 @default.
- W4290943605 hasRelatedWork W2360601255 @default.
- W4290943605 hasRelatedWork W2961085424 @default.
- W4290943605 hasRelatedWork W3090337104 @default.
- W4290943605 hasRelatedWork W3201070945 @default.
- W4290943605 hasRelatedWork W4289860834 @default.
- W4290943605 hasRelatedWork W4306674287 @default.
- W4290943605 isParatext "false" @default.
- W4290943605 isRetracted "false" @default.
- W4290943605 workType "article" @default.