FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4320731432> ?p ?o ?g. }

• W4320731432 endingPage "110394" @default.
• W4320731432 startingPage "110394" @default.
• W4320731432 abstract "With the continuous addition of new classes of data, incremental learning is widely followed and studied, especially for few-shot scenarios. Few-shot class incremental learning (FSCIL) aims to continually learn new knowledge with limited data, without forgetting old knowledge. Owing to limited new class samples and special incremental processes, FSCIL faces the problems of old knowledge catastrophic forgetting and new class adaption. We focus on a multi-feature space similarity supplement (MFS3) to alleviate the two dilemmas. We first train different feature spaces for different sessions, and use an inter-feature space similarity supplement (IFS3) to focus on boundary-sensitive sample points to improve the expression ability of every single session. To handle old knowledge catastrophic forgetting, we use the base feature space as the major and take multiple new feature spaces as supplements. For better adaption of new classes, we further design an outer-feature space similarity supplement (OFS3). OFS3 can utilize the supplement of base feature space with new feature space to rejudge the sample points, whose similarity results of base feature space are changed due to the addition of new classes. In general, IFS3 facilitates a single session, while OFS3 contributes a multi-feature space similarity supplement between different sessions in FSCIL. Sufficient experiments on three benchmark datasets, including CIFAR100, miniImageNet, and CUB200 demonstrate the advantage of our method. With the multi-feature space similarity supplement strategy, our method outperforms the state-of-the-art approaches by a large margin." @default.
• W4320731432 created "2023-02-15" @default.
• W4320731432 creator A5005020565 @default.
• W4320731432 creator A5010841617 @default.
• W4320731432 creator A5011272577 @default.
• W4320731432 creator A5022550580 @default.
• W4320731432 creator A5068016767 @default.
• W4320731432 creator A5089085075 @default.
• W4320731432 date "2023-04-01" @default.
• W4320731432 modified "2023-09-23" @default.
• W4320731432 title "Multi-feature space similarity supplement for few-shot class incremental learning" @default.
• W4320731432 cites W1996638368 @default.
• W4320731432 cites W2025183033 @default.
• W4320731432 cites W2049017883 @default.
• W4320731432 cites W2110940238 @default.
• W4320731432 cites W2117539524 @default.
• W4320731432 cites W2158207287 @default.
• W4320731432 cites W2498789492 @default.
• W4320731432 cites W2521365688 @default.
• W4320731432 cites W2625674597 @default.
• W4320731432 cites W2884282566 @default.
• W4320731432 cites W2914337210 @default.
• W4320731432 cites W2948734064 @default.
• W4320731432 cites W2954996726 @default.
• W4320731432 cites W2963769056 @default.
• W4320731432 cites W2964137095 @default.
• W4320731432 cites W2964189064 @default.
• W4320731432 cites W2984260139 @default.
• W4320731432 cites W3000870854 @default.
• W4320731432 cites W3012255272 @default.
• W4320731432 cites W3034942609 @default.
• W4320731432 cites W3035342403 @default.
• W4320731432 cites W3035501943 @default.
• W4320731432 cites W3093670440 @default.
• W4320731432 cites W3135126802 @default.
• W4320731432 cites W3165181705 @default.
• W4320731432 cites W3175270254 @default.
• W4320731432 cites W3175771944 @default.
• W4320731432 cites W3177494822 @default.
• W4320731432 cites W3182874523 @default.
• W4320731432 cites W3187986157 @default.
• W4320731432 cites W3205249428 @default.
• W4320731432 cites W3205633403 @default.
• W4320731432 cites W4210667047 @default.
• W4320731432 cites W4214807529 @default.
• W4320731432 cites W4220941681 @default.
• W4320731432 cites W4221090720 @default.
• W4320731432 doi "https://doi.org/10.1016/j.knosys.2023.110394" @default.
• W4320731432 hasPublicationYear "2023" @default.
• W4320731432 type Work @default.
• W4320731432 citedByCount "0" @default.
• W4320731432 crossrefType "journal-article" @default.
• W4320731432 hasAuthorship W4320731432A5005020565 @default.
• W4320731432 hasAuthorship W4320731432A5010841617 @default.
• W4320731432 hasAuthorship W4320731432A5011272577 @default.
• W4320731432 hasAuthorship W4320731432A5022550580 @default.
• W4320731432 hasAuthorship W4320731432A5068016767 @default.
• W4320731432 hasAuthorship W4320731432A5089085075 @default.
• W4320731432 hasConcept C103278499 @default.
• W4320731432 hasConcept C115961682 @default.
• W4320731432 hasConcept C119857082 @default.
• W4320731432 hasConcept C120665830 @default.
• W4320731432 hasConcept C121332964 @default.
• W4320731432 hasConcept C124101348 @default.
• W4320731432 hasConcept C13280743 @default.
• W4320731432 hasConcept C138885662 @default.
• W4320731432 hasConcept C153180895 @default.
• W4320731432 hasConcept C154945302 @default.
• W4320731432 hasConcept C185798385 @default.
• W4320731432 hasConcept C192209626 @default.
• W4320731432 hasConcept C205649164 @default.
• W4320731432 hasConcept C2776401178 @default.
• W4320731432 hasConcept C2777212361 @default.
• W4320731432 hasConcept C41008148 @default.
• W4320731432 hasConcept C41895202 @default.
• W4320731432 hasConcept C59404180 @default.
• W4320731432 hasConcept C7149132 @default.
• W4320731432 hasConcept C774472 @default.
• W4320731432 hasConcept C83665646 @default.
• W4320731432 hasConceptScore W4320731432C103278499 @default.
• W4320731432 hasConceptScore W4320731432C115961682 @default.
• W4320731432 hasConceptScore W4320731432C119857082 @default.
• W4320731432 hasConceptScore W4320731432C120665830 @default.
• W4320731432 hasConceptScore W4320731432C121332964 @default.
• W4320731432 hasConceptScore W4320731432C124101348 @default.
• W4320731432 hasConceptScore W4320731432C13280743 @default.
• W4320731432 hasConceptScore W4320731432C138885662 @default.
• W4320731432 hasConceptScore W4320731432C153180895 @default.
• W4320731432 hasConceptScore W4320731432C154945302 @default.
• W4320731432 hasConceptScore W4320731432C185798385 @default.
• W4320731432 hasConceptScore W4320731432C192209626 @default.
• W4320731432 hasConceptScore W4320731432C205649164 @default.
• W4320731432 hasConceptScore W4320731432C2776401178 @default.
• W4320731432 hasConceptScore W4320731432C2777212361 @default.
• W4320731432 hasConceptScore W4320731432C41008148 @default.
• W4320731432 hasConceptScore W4320731432C41895202 @default.
• W4320731432 hasConceptScore W4320731432C59404180 @default.
• W4320731432 hasConceptScore W4320731432C7149132 @default.

• next