Matches in SemOpenAlex for { <https://semopenalex.org/work/W3159650566> ?p ?o ?g. }
- W3159650566 abstract "Continual learning of new knowledge over time is one desirable capability for intelligent systems to recognize more and more classes of objects. Without or with very limited amount of old data stored, an intelligent system often catastrophically forgets previously learned old knowledge when learning new knowledge. Recently, various approaches have been proposed to alleviate the catastrophic forgetting issue. However, old knowledge learned earlier is commonly less preserved than that learned more recently. In order to reduce the forgetting of particularly earlier learned old knowledge and improve the overall continual learning performance, we propose a simple yet effective fusion mechanism by including all the previously learned feature extractors into the intelligent model. In addition, a new feature extractor is included to the model when learning a new set of classes each time, and a feature extractor pruning is also applied to prevent the whole model size from growing rapidly. Experiments on multiple classification tasks show that the proposed approach can effectively reduce the forgetting of old knowledge, achieving state-of-the-art continual learning performance." @default.
- W3159650566 created "2021-05-10" @default.
- W3159650566 creator A5002976916 @default.
- W3159650566 creator A5043493705 @default.
- W3159650566 creator A5051509417 @default.
- W3159650566 creator A5052483331 @default.
- W3159650566 creator A5082605318 @default.
- W3159650566 date "2021-04-28" @default.
- W3159650566 modified "2023-09-23" @default.
- W3159650566 title "Preserving Earlier Knowledge in Continual Learning with the Help of All Previous Feature Extractors." @default.
- W3159650566 cites W2108598243 @default.
- W3159650566 cites W2113839990 @default.
- W3159650566 cites W2401231614 @default.
- W3159650566 cites W2473930607 @default.
- W3159650566 cites W2554616628 @default.
- W3159650566 cites W2560647685 @default.
- W3159650566 cites W2583761661 @default.
- W3159650566 cites W2744654301 @default.
- W3159650566 cites W2803620993 @default.
- W3159650566 cites W2884282566 @default.
- W3159650566 cites W2895723011 @default.
- W3159650566 cites W2948734064 @default.
- W3159650566 cites W2954929116 @default.
- W3159650566 cites W2963072899 @default.
- W3159650566 cites W2963157804 @default.
- W3159650566 cites W2963420686 @default.
- W3159650566 cites W2963438784 @default.
- W3159650566 cites W2963559848 @default.
- W3159650566 cites W2963560049 @default.
- W3159650566 cites W2963588172 @default.
- W3159650566 cites W2963876099 @default.
- W3159650566 cites W2964189064 @default.
- W3159650566 cites W2965661443 @default.
- W3159650566 cites W2970199615 @default.
- W3159650566 cites W2970502342 @default.
- W3159650566 cites W2970748152 @default.
- W3159650566 cites W2971234316 @default.
- W3159650566 cites W2972313371 @default.
- W3159650566 cites W2981864462 @default.
- W3159650566 cites W2982410595 @default.
- W3159650566 cites W2995139074 @default.
- W3159650566 cites W3034856281 @default.
- W3159650566 cites W3034867292 @default.
- W3159650566 cites W3035157843 @default.
- W3159650566 cites W3035546118 @default.
- W3159650566 cites W3094953068 @default.
- W3159650566 cites W3107810305 @default.
- W3159650566 cites W3108280718 @default.
- W3159650566 cites W3118608800 @default.
- W3159650566 cites W3180392831 @default.
- W3159650566 hasPublicationYear "2021" @default.
- W3159650566 type Work @default.
- W3159650566 sameAs 3159650566 @default.
- W3159650566 citedByCount "0" @default.
- W3159650566 crossrefType "posted-content" @default.
- W3159650566 hasAuthorship W3159650566A5002976916 @default.
- W3159650566 hasAuthorship W3159650566A5043493705 @default.
- W3159650566 hasAuthorship W3159650566A5051509417 @default.
- W3159650566 hasAuthorship W3159650566A5052483331 @default.
- W3159650566 hasAuthorship W3159650566A5082605318 @default.
- W3159650566 hasConcept C108010975 @default.
- W3159650566 hasConcept C117978034 @default.
- W3159650566 hasConcept C119857082 @default.
- W3159650566 hasConcept C127413603 @default.
- W3159650566 hasConcept C138885662 @default.
- W3159650566 hasConcept C154945302 @default.
- W3159650566 hasConcept C177264268 @default.
- W3159650566 hasConcept C199360897 @default.
- W3159650566 hasConcept C21880701 @default.
- W3159650566 hasConcept C2776401178 @default.
- W3159650566 hasConcept C41008148 @default.
- W3159650566 hasConcept C41895202 @default.
- W3159650566 hasConcept C6557445 @default.
- W3159650566 hasConcept C7149132 @default.
- W3159650566 hasConcept C86803240 @default.
- W3159650566 hasConceptScore W3159650566C108010975 @default.
- W3159650566 hasConceptScore W3159650566C117978034 @default.
- W3159650566 hasConceptScore W3159650566C119857082 @default.
- W3159650566 hasConceptScore W3159650566C127413603 @default.
- W3159650566 hasConceptScore W3159650566C138885662 @default.
- W3159650566 hasConceptScore W3159650566C154945302 @default.
- W3159650566 hasConceptScore W3159650566C177264268 @default.
- W3159650566 hasConceptScore W3159650566C199360897 @default.
- W3159650566 hasConceptScore W3159650566C21880701 @default.
- W3159650566 hasConceptScore W3159650566C2776401178 @default.
- W3159650566 hasConceptScore W3159650566C41008148 @default.
- W3159650566 hasConceptScore W3159650566C41895202 @default.
- W3159650566 hasConceptScore W3159650566C6557445 @default.
- W3159650566 hasConceptScore W3159650566C7149132 @default.
- W3159650566 hasConceptScore W3159650566C86803240 @default.
- W3159650566 hasLocation W31596505661 @default.
- W3159650566 hasOpenAccess W3159650566 @default.
- W3159650566 hasPrimaryLocation W31596505661 @default.
- W3159650566 hasRelatedWork W2805228670 @default.
- W3159650566 hasRelatedWork W2892331934 @default.
- W3159650566 hasRelatedWork W2902456977 @default.
- W3159650566 hasRelatedWork W2903183390 @default.
- W3159650566 hasRelatedWork W2947612752 @default.
- W3159650566 hasRelatedWork W2967588839 @default.
- W3159650566 hasRelatedWork W3000677656 @default.