Matches in SemOpenAlex for { <https://semopenalex.org/work/W4289097880> ?p ?o ?g. }
Showing items 1 to 39 of
39
with 100 items per page.
- W4289097880 abstract "So far life-long learning (LLL) has been studied in relatively small-scale and relatively artificial setups. Here, we introduce a new large-scale alternative. What makes the proposed setup more natural and closer to human-like visual systems is threefold: First, we focus on concepts (or facts, as we call them) of varying complexity, ranging from single objects to more complex structures such as objects performing actions, and objects interacting with other objects. Second, as in real-world settings, our setup has a long-tail distribution, an aspect which has mostly been ignored in the LLL context. Third, facts across tasks may share structure (e.g., <person, riding, wave> and <dog, riding, wave>). Facts can also be semantically related (e.g., liger relates to seen categories like tiger and lion). Given the large number of possible facts, a LLL setup seems a natural choice. To avoid model size growing over time and to optimally exploit the semantic relations and structure, we combine it with a visual semantic embedding instead of discrete class labels. We adapt existing datasets with the properties mentioned above into new benchmarks, by dividing them semantically or randomly into disjoint tasks. This leads to two large-scale benchmarks with 906,232 images and 165,150 unique facts, on which we evaluate and analyze state-of-the-art LLL methods." @default.
- W4289097880 created "2022-08-01" @default.
- W4289097880 creator A5021198356 @default.
- W4289097880 creator A5024481540 @default.
- W4289097880 creator A5051613830 @default.
- W4289097880 creator A5054437548 @default.
- W4289097880 creator A5074816094 @default.
- W4289097880 creator A5085089542 @default.
- W4289097880 date "2018-12-26" @default.
- W4289097880 modified "2023-09-23" @default.
- W4289097880 title "Exploring the Challenges towards Lifelong Fact Learning" @default.
- W4289097880 doi "https://doi.org/10.48550/arxiv.1812.10524" @default.
- W4289097880 hasPublicationYear "2018" @default.
- W4289097880 type Work @default.
- W4289097880 citedByCount "0" @default.
- W4289097880 crossrefType "posted-content" @default.
- W4289097880 hasAuthorship W4289097880A5021198356 @default.
- W4289097880 hasAuthorship W4289097880A5024481540 @default.
- W4289097880 hasAuthorship W4289097880A5051613830 @default.
- W4289097880 hasAuthorship W4289097880A5054437548 @default.
- W4289097880 hasAuthorship W4289097880A5074816094 @default.
- W4289097880 hasAuthorship W4289097880A5085089542 @default.
- W4289097880 hasBestOaLocation W42890978801 @default.
- W4289097880 hasConcept C108771440 @default.
- W4289097880 hasConcept C15744967 @default.
- W4289097880 hasConcept C19417346 @default.
- W4289097880 hasConcept C41008148 @default.
- W4289097880 hasConcept C56739046 @default.
- W4289097880 hasConceptScore W4289097880C108771440 @default.
- W4289097880 hasConceptScore W4289097880C15744967 @default.
- W4289097880 hasConceptScore W4289097880C19417346 @default.
- W4289097880 hasConceptScore W4289097880C41008148 @default.
- W4289097880 hasConceptScore W4289097880C56739046 @default.
- W4289097880 hasLocation W42890978801 @default.
- W4289097880 hasOpenAccess W4289097880 @default.
- W4289097880 hasPrimaryLocation W42890978801 @default.
- W4289097880 isParatext "false" @default.
- W4289097880 isRetracted "false" @default.
- W4289097880 workType "article" @default.