Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385301178> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W4385301178 abstract "Neural network models have achieved great success in numerous disciplines in recent years, including image segmentation, object identification, and natural language processing (NLP). Incremental learning in these fields focuses on training models in a continuous data stream. As time goes by, more new data becomes available, and old data may become unavailable owing to resource constraints such as storage. As a result, when new data is continually arriving, the performance of the neural network model on the old data sample sometimes decreases significantly, a phenomenon known as catastrophic forgetting. Many corresponding strategies have been proposed to mitigate the catastrophic forgetting of neural network models, which are based on parameter regularization, data replay, and parameter isolation. This paper proposes an incremental learning method based on data feature distribution (ICFD). The method uses Gaussian distribution to generate features from old data to train neural network models based on the phenomenon that feature vectors obey multi-dimensional Gaussian distribution in feature space. This method avoids storing a large number of original samples, and the generated old class features contain more sample information. This method combines data playback and parameter regularization in concrete implementation. The experimental results of ICFD on the CIFAR-100 demonstrate that when the incremental step is 5, the average incremental accuracy is increased by 10.4%. When the incremental step is 10, the average incremental accuracy is improved by 8.1%." @default.
- W4385301178 created "2023-07-28" @default.
- W4385301178 creator A5034435564 @default.
- W4385301178 creator A5036347970 @default.
- W4385301178 creator A5063949671 @default.
- W4385301178 creator A5075737786 @default.
- W4385301178 creator A5076667050 @default.
- W4385301178 date "2022-12-01" @default.
- W4385301178 modified "2023-09-26" @default.
- W4385301178 title "ICFD: An Incremental Learning Method Based on Data Feature Distribution" @default.
- W4385301178 cites W1682403713 @default.
- W4385301178 cites W2194775991 @default.
- W4385301178 cites W2473930607 @default.
- W4385301178 cites W2560647685 @default.
- W4385301178 cites W2948734064 @default.
- W4385301178 cites W2954929116 @default.
- W4385301178 cites W2963072899 @default.
- W4385301178 cites W2964189064 @default.
- W4385301178 cites W2998290232 @default.
- W4385301178 cites W3034856281 @default.
- W4385301178 cites W3035060563 @default.
- W4385301178 cites W3035501943 @default.
- W4385301178 cites W3097784654 @default.
- W4385301178 cites W3102701618 @default.
- W4385301178 cites W3107810305 @default.
- W4385301178 cites W3127228978 @default.
- W4385301178 cites W3168149265 @default.
- W4385301178 cites W3175294706 @default.
- W4385301178 cites W3175853876 @default.
- W4385301178 cites W3208194557 @default.
- W4385301178 cites W3208750293 @default.
- W4385301178 cites W3210573383 @default.
- W4385301178 cites W4221152131 @default.
- W4385301178 cites W4226134030 @default.
- W4385301178 cites W4226219101 @default.
- W4385301178 cites W4240361565 @default.
- W4385301178 cites W4312327301 @default.
- W4385301178 cites W4312603992 @default.
- W4385301178 cites W4313138032 @default.
- W4385301178 cites W3174083140 @default.
- W4385301178 doi "https://doi.org/10.1109/smartworld-uic-atc-scalcom-digitaltwin-pricomp-metaverse56740.2022.00103" @default.
- W4385301178 hasPublicationYear "2022" @default.
- W4385301178 type Work @default.
- W4385301178 citedByCount "0" @default.
- W4385301178 crossrefType "proceedings-article" @default.
- W4385301178 hasAuthorship W4385301178A5034435564 @default.
- W4385301178 hasAuthorship W4385301178A5036347970 @default.
- W4385301178 hasAuthorship W4385301178A5063949671 @default.
- W4385301178 hasAuthorship W4385301178A5075737786 @default.
- W4385301178 hasAuthorship W4385301178A5076667050 @default.
- W4385301178 hasConcept C119857082 @default.
- W4385301178 hasConcept C124101348 @default.
- W4385301178 hasConcept C138885662 @default.
- W4385301178 hasConcept C153180895 @default.
- W4385301178 hasConcept C154945302 @default.
- W4385301178 hasConcept C2776135515 @default.
- W4385301178 hasConcept C2776401178 @default.
- W4385301178 hasConcept C2780735816 @default.
- W4385301178 hasConcept C41008148 @default.
- W4385301178 hasConcept C41895202 @default.
- W4385301178 hasConcept C50644808 @default.
- W4385301178 hasConcept C7149132 @default.
- W4385301178 hasConcept C83665646 @default.
- W4385301178 hasConceptScore W4385301178C119857082 @default.
- W4385301178 hasConceptScore W4385301178C124101348 @default.
- W4385301178 hasConceptScore W4385301178C138885662 @default.
- W4385301178 hasConceptScore W4385301178C153180895 @default.
- W4385301178 hasConceptScore W4385301178C154945302 @default.
- W4385301178 hasConceptScore W4385301178C2776135515 @default.
- W4385301178 hasConceptScore W4385301178C2776401178 @default.
- W4385301178 hasConceptScore W4385301178C2780735816 @default.
- W4385301178 hasConceptScore W4385301178C41008148 @default.
- W4385301178 hasConceptScore W4385301178C41895202 @default.
- W4385301178 hasConceptScore W4385301178C50644808 @default.
- W4385301178 hasConceptScore W4385301178C7149132 @default.
- W4385301178 hasConceptScore W4385301178C83665646 @default.
- W4385301178 hasFunder F4320306076 @default.
- W4385301178 hasLocation W43853011781 @default.
- W4385301178 hasOpenAccess W4385301178 @default.
- W4385301178 hasPrimaryLocation W43853011781 @default.
- W4385301178 hasRelatedWork W2060018656 @default.
- W4385301178 hasRelatedWork W2065448819 @default.
- W4385301178 hasRelatedWork W2293915134 @default.
- W4385301178 hasRelatedWork W2382607599 @default.
- W4385301178 hasRelatedWork W2517539590 @default.
- W4385301178 hasRelatedWork W2546942002 @default.
- W4385301178 hasRelatedWork W2944661354 @default.
- W4385301178 hasRelatedWork W2970216048 @default.
- W4385301178 hasRelatedWork W3047965787 @default.
- W4385301178 hasRelatedWork W2886616187 @default.
- W4385301178 isParatext "false" @default.
- W4385301178 isRetracted "false" @default.
- W4385301178 workType "article" @default.