Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366197193> ?p ?o ?g. }
Showing items 1 to 49 of
49
with 100 items per page.
- W4366197193 abstract "Out-of-distribution (OOD) detection aims to identify test examples that do not belong to the training distribution and are thus unlikely to be predicted reliably. Despite a plethora of existing works, most of them focused only on the scenario where OOD examples come from semantic shift (e.g., unseen categories), ignoring other possible causes (e.g., covariate shift). In this paper, we present a novel, unifying framework to study OOD detection in a broader scope. Instead of detecting OOD examples from a particular cause, we propose to detect examples that a deployed machine learning model (e.g., an image classifier) is unable to predict correctly. That is, whether a test example should be detected and rejected or not is ``model-specific''. We show that this framework unifies the detection of OOD examples caused by semantic shift and covariate shift, and closely addresses the concern of applying a machine learning model to uncontrolled environments. We provide an extensive analysis that involves a variety of models (e.g., different architectures and training strategies), sources of OOD examples, and OOD detection approaches, and reveal several insights into improving and understanding OOD detection in uncontrolled environments." @default.
- W4366197193 created "2023-04-19" @default.
- W4366197193 creator A5018066903 @default.
- W4366197193 creator A5082347207 @default.
- W4366197193 date "2023-04-13" @default.
- W4366197193 modified "2023-09-24" @default.
- W4366197193 title "Unified Out-Of-Distribution Detection: A Model-Specific Perspective" @default.
- W4366197193 doi "https://doi.org/10.48550/arxiv.2304.06813" @default.
- W4366197193 hasPublicationYear "2023" @default.
- W4366197193 type Work @default.
- W4366197193 citedByCount "0" @default.
- W4366197193 crossrefType "posted-content" @default.
- W4366197193 hasAuthorship W4366197193A5018066903 @default.
- W4366197193 hasAuthorship W4366197193A5082347207 @default.
- W4366197193 hasBestOaLocation W43661971931 @default.
- W4366197193 hasConcept C119043178 @default.
- W4366197193 hasConcept C119857082 @default.
- W4366197193 hasConcept C12713177 @default.
- W4366197193 hasConcept C136197465 @default.
- W4366197193 hasConcept C154945302 @default.
- W4366197193 hasConcept C199360897 @default.
- W4366197193 hasConcept C2778012447 @default.
- W4366197193 hasConcept C41008148 @default.
- W4366197193 hasConcept C95623464 @default.
- W4366197193 hasConceptScore W4366197193C119043178 @default.
- W4366197193 hasConceptScore W4366197193C119857082 @default.
- W4366197193 hasConceptScore W4366197193C12713177 @default.
- W4366197193 hasConceptScore W4366197193C136197465 @default.
- W4366197193 hasConceptScore W4366197193C154945302 @default.
- W4366197193 hasConceptScore W4366197193C199360897 @default.
- W4366197193 hasConceptScore W4366197193C2778012447 @default.
- W4366197193 hasConceptScore W4366197193C41008148 @default.
- W4366197193 hasConceptScore W4366197193C95623464 @default.
- W4366197193 hasLocation W43661971931 @default.
- W4366197193 hasOpenAccess W4366197193 @default.
- W4366197193 hasPrimaryLocation W43661971931 @default.
- W4366197193 hasRelatedWork W2009596306 @default.
- W4366197193 hasRelatedWork W2512018286 @default.
- W4366197193 hasRelatedWork W2556319748 @default.
- W4366197193 hasRelatedWork W2891961174 @default.
- W4366197193 hasRelatedWork W2961085424 @default.
- W4366197193 hasRelatedWork W3158264953 @default.
- W4366197193 hasRelatedWork W3200179079 @default.
- W4366197193 hasRelatedWork W4211088005 @default.
- W4366197193 hasRelatedWork W4249229055 @default.
- W4366197193 hasRelatedWork W4310989423 @default.
- W4366197193 isParatext "false" @default.
- W4366197193 isRetracted "false" @default.
- W4366197193 workType "article" @default.