FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912861356> ?p ?o ?g. }

• W2912861356 abstract "In order to apply a convolutional neural network (CNN) to unseen datasets, a common way is to train a CNN using a pre-trained model on a big dataset by fine-tuning it instead of starting from scratch. How to control the fine-tuning progress to get the desired properties is still a challenging problem. Our key observation is that the visual features of the pre-trained model have rich information and can be explored during the training process. A natural thought is to employ these features and design a control strategy to improve the performance of the transfer learning process. In this paper, a procedural learning framework using the learned low-rank component of the visual features both in the pre-trained model and the training process is proposed to improve the accuracy and generalizability of the CNN. In this framework, we presented an approach to yield independent visualization features (IVFs). We found via robust independent component analysis that the low-rank components of IVFs provided robust features for our framework. Then, we design a Wasserstein regularization to control the transportation of the distribution of IVFs from a pre-trained model to a final model via the Wasserstein distance. The experiments on the Cifar-10 and Cifar-100 datasets via a VGG-style CNN model showed that our method effectively improves the classification results and convergence speed. The basic idea is that exploring visual features can also potentially inspire other topics, such as image detection and reinforcement learning." @default.
• W2912861356 created "2019-02-21" @default.
• W2912861356 creator A5007291380 @default.
• W2912861356 creator A5020746135 @default.
• W2912861356 creator A5030897972 @default.
• W2912861356 creator A5041636373 @default.
• W2912861356 creator A5059100653 @default.
• W2912861356 creator A5070695637 @default.
• W2912861356 date "2019-01-01" @default.
• W2912861356 modified "2023-10-13" @default.
• W2912861356 title "Procedural Learning With Robust Visual Features via Low Rank Prior" @default.
• W2912861356 cites W1565327149 @default.
• W2912861356 cites W1686810756 @default.
• W2912861356 cites W1915485278 @default.
• W2912861356 cites W198034206 @default.
• W2912861356 cites W2079639858 @default.
• W2912861356 cites W2102368172 @default.
• W2912861356 cites W2108598243 @default.
• W2912861356 cites W2120580172 @default.
• W2912861356 cites W2131628350 @default.
• W2912861356 cites W2145962650 @default.
• W2912861356 cites W2158131535 @default.
• W2912861356 cites W2159291411 @default.
• W2912861356 cites W2163605009 @default.
• W2912861356 cites W2165698076 @default.
• W2912861356 cites W2418098761 @default.
• W2912861356 cites W2557449848 @default.
• W2912861356 cites W2557873547 @default.
• W2912861356 cites W2593267444 @default.
• W2912861356 cites W2593634001 @default.
• W2912861356 cites W2625270925 @default.
• W2912861356 cites W2626107033 @default.
• W2912861356 cites W2734811486 @default.
• W2912861356 cites W2757545780 @default.
• W2912861356 cites W2778500870 @default.
• W2912861356 cites W2826685045 @default.
• W2912861356 cites W2919115771 @default.
• W2912861356 cites W2949667497 @default.
• W2912861356 cites W2962879692 @default.
• W2912861356 cites W2964333607 @default.
• W2912861356 cites W3105409087 @default.
• W2912861356 cites W562660536 @default.
• W2912861356 doi "https://doi.org/10.1109/access.2019.2894841" @default.
• W2912861356 hasPublicationYear "2019" @default.
• W2912861356 type Work @default.
• W2912861356 sameAs 2912861356 @default.
• W2912861356 citedByCount "0" @default.
• W2912861356 crossrefType "journal-article" @default.
• W2912861356 hasAuthorship W2912861356A5007291380 @default.
• W2912861356 hasAuthorship W2912861356A5020746135 @default.
• W2912861356 hasAuthorship W2912861356A5030897972 @default.
• W2912861356 hasAuthorship W2912861356A5041636373 @default.
• W2912861356 hasAuthorship W2912861356A5059100653 @default.
• W2912861356 hasAuthorship W2912861356A5070695637 @default.
• W2912861356 hasBestOaLocation W29128613561 @default.
• W2912861356 hasConcept C104317684 @default.
• W2912861356 hasConcept C111919701 @default.
• W2912861356 hasConcept C115961682 @default.
• W2912861356 hasConcept C119857082 @default.
• W2912861356 hasConcept C150899416 @default.
• W2912861356 hasConcept C153180895 @default.
• W2912861356 hasConcept C154945302 @default.
• W2912861356 hasConcept C185592680 @default.
• W2912861356 hasConcept C36464697 @default.
• W2912861356 hasConcept C41008148 @default.
• W2912861356 hasConcept C55493867 @default.
• W2912861356 hasConcept C63479239 @default.
• W2912861356 hasConcept C75294576 @default.
• W2912861356 hasConcept C81363708 @default.
• W2912861356 hasConcept C98045186 @default.
• W2912861356 hasConceptScore W2912861356C104317684 @default.
• W2912861356 hasConceptScore W2912861356C111919701 @default.
• W2912861356 hasConceptScore W2912861356C115961682 @default.
• W2912861356 hasConceptScore W2912861356C119857082 @default.
• W2912861356 hasConceptScore W2912861356C150899416 @default.
• W2912861356 hasConceptScore W2912861356C153180895 @default.
• W2912861356 hasConceptScore W2912861356C154945302 @default.
• W2912861356 hasConceptScore W2912861356C185592680 @default.
• W2912861356 hasConceptScore W2912861356C36464697 @default.
• W2912861356 hasConceptScore W2912861356C41008148 @default.
• W2912861356 hasConceptScore W2912861356C55493867 @default.
• W2912861356 hasConceptScore W2912861356C63479239 @default.
• W2912861356 hasConceptScore W2912861356C75294576 @default.
• W2912861356 hasConceptScore W2912861356C81363708 @default.
• W2912861356 hasConceptScore W2912861356C98045186 @default.
• W2912861356 hasFunder F4320321001 @default.
• W2912861356 hasFunder F4320322843 @default.
• W2912861356 hasLocation W29128613561 @default.
• W2912861356 hasLocation W29128613562 @default.
• W2912861356 hasOpenAccess W2912861356 @default.
• W2912861356 hasPrimaryLocation W29128613561 @default.
• W2912861356 hasRelatedWork W1786507113 @default.
• W2912861356 hasRelatedWork W2101626488 @default.
• W2912861356 hasRelatedWork W2104465941 @default.
• W2912861356 hasRelatedWork W2181771597 @default.
• W2912861356 hasRelatedWork W2293317945 @default.
• W2912861356 hasRelatedWork W2499321295 @default.
• W2912861356 hasRelatedWork W2801886677 @default.
• W2912861356 hasRelatedWork W2923100990 @default.
• W2912861356 hasRelatedWork W3130740428 @default.

• next