FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387117114> ?p ?o ?g. }

• W4387117114 endingPage "121829" @default.
• W4387117114 startingPage "121829" @default.
• W4387117114 abstract "The out-of-distribution (OOD) detection task assumes samples that follow the distribution of training data as in-distribution (ID), while samples from other data distributions are considered OOD. In recent years, the OOD detection tasks have made significant progress since many studies observed that the distribution mismatch between training and real datasets can severely deteriorate the reliability of AI systems. Nevertheless, the lack of precise interpretation for the in-distribution (ID) limits the application of the OOD detection methods to real-world systems. To tackle this, we decompose the definition of the ID into texture and semantics, motivated by the demands of real-world scenarios. We also design new benchmarks to measure the robustness that OOD detection methods should have. Our proposed benchmark verifies not only the precision but also the robustness of the detection models. It is crucial to measure both factors in OOD detection as they indicate different traits of the model. For instance, precision is relevant to scenarios that detect minor cracks in the conveyor belt of a smart factory, whereas robustness pertains to maintaining performance under diverse weather conditions, as required by autonomous driving. To achieve a good balance between the OOD detection performance and robustness, our method takes a divide-and-conquer approach. Specifically, the proposed model first handles each component of the texture and semantics separately and then fuses these later. This philosophy is empirically proven by a series of benchmarks including both the proposed and the conventional counterpart. By decomposing the prior “unclear” definition of the ID into texture and semantic components, our novel approach better suits the demands of a reliable machine learning system, which requires robustness and consistent performance across varied scenarios. Unlike prior works, our approach does not rely on any extra datasets or labels. This prevents our proposed framework from being dependent on a particular dataset distribution." @default.
• W4387117114 created "2023-09-29" @default.
• W4387117114 creator A5046027097 @default.
• W4387117114 creator A5047656074 @default.
• W4387117114 creator A5051011750 @default.
• W4387117114 date "2024-03-01" @default.
• W4387117114 modified "2023-10-15" @default.
• W4387117114 title "Decomposing texture and semantic for out-of-distribution detection" @default.
• W4387117114 cites W2047643928 @default.
• W4387117114 cites W2145607950 @default.
• W4387117114 cites W2732026016 @default.
• W4387117114 cites W2902817737 @default.
• W4387117114 cites W2944691132 @default.
• W4387117114 cites W2990064013 @default.
• W4387117114 cites W2997167991 @default.
• W4387117114 cites W2997212544 @default.
• W4387117114 cites W3010244393 @default.
• W4387117114 cites W3034230713 @default.
• W4387117114 cites W3034771037 @default.
• W4387117114 cites W3035524453 @default.
• W4387117114 cites W3177464700 @default.
• W4387117114 cites W3195401276 @default.
• W4387117114 cites W3208955241 @default.
• W4387117114 cites W4226288807 @default.
• W4387117114 cites W4283512325 @default.
• W4387117114 cites W4309293762 @default.
• W4387117114 cites W4311091133 @default.
• W4387117114 cites W4361275963 @default.
• W4387117114 cites W4362508096 @default.
• W4387117114 cites W4362581238 @default.
• W4387117114 cites W4365509076 @default.
• W4387117114 cites W4367310953 @default.
• W4387117114 cites W4379380034 @default.
• W4387117114 cites W4382463911 @default.
• W4387117114 cites W4386066643 @default.
• W4387117114 doi "https://doi.org/10.1016/j.eswa.2023.121829" @default.
• W4387117114 hasPublicationYear "2024" @default.
• W4387117114 type Work @default.
• W4387117114 citedByCount "0" @default.
• W4387117114 crossrefType "journal-article" @default.
• W4387117114 hasAuthorship W4387117114A5046027097 @default.
• W4387117114 hasAuthorship W4387117114A5047656074 @default.
• W4387117114 hasAuthorship W4387117114A5051011750 @default.
• W4387117114 hasBestOaLocation W43871171141 @default.
• W4387117114 hasConcept C104317684 @default.
• W4387117114 hasConcept C119857082 @default.
• W4387117114 hasConcept C124101348 @default.
• W4387117114 hasConcept C154945302 @default.
• W4387117114 hasConcept C185592680 @default.
• W4387117114 hasConcept C41008148 @default.
• W4387117114 hasConcept C55493867 @default.
• W4387117114 hasConcept C63479239 @default.
• W4387117114 hasConceptScore W4387117114C104317684 @default.
• W4387117114 hasConceptScore W4387117114C119857082 @default.
• W4387117114 hasConceptScore W4387117114C124101348 @default.
• W4387117114 hasConceptScore W4387117114C154945302 @default.
• W4387117114 hasConceptScore W4387117114C185592680 @default.
• W4387117114 hasConceptScore W4387117114C41008148 @default.
• W4387117114 hasConceptScore W4387117114C55493867 @default.
• W4387117114 hasConceptScore W4387117114C63479239 @default.
• W4387117114 hasLocation W43871171141 @default.
• W4387117114 hasOpenAccess W4387117114 @default.
• W4387117114 hasPrimaryLocation W43871171141 @default.
• W4387117114 hasRelatedWork W2961085424 @default.
• W4387117114 hasRelatedWork W3046775127 @default.
• W4387117114 hasRelatedWork W3107602296 @default.
• W4387117114 hasRelatedWork W3170094116 @default.
• W4387117114 hasRelatedWork W3209574120 @default.
• W4387117114 hasRelatedWork W4210805261 @default.
• W4387117114 hasRelatedWork W4306674287 @default.
• W4387117114 hasRelatedWork W4312192474 @default.
• W4387117114 hasRelatedWork W4386462264 @default.
• W4387117114 hasRelatedWork W4387297750 @default.
• W4387117114 hasVolume "238" @default.
• W4387117114 isParatext "false" @default.
• W4387117114 isRetracted "false" @default.
• W4387117114 workType "article" @default.