Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285604194> ?p ?o ?g. }
Showing items 1 to 59 of
59
with 100 items per page.
- W4285604194 abstract "Deep neural networks (DNNs) have achieved excellent results currently in classification, while they may still suffer from ambiguous images which are similar across classes. By contrast, humans have a relatively good ability to distinguish these categories of images. Therefore, we propose a human-in-the-loop solution to assist the network to better classify the images by leveraging human knowledge. To achieve this, we project the high-dimensional latent space trained by the network onto a two-dimensional workspace. The users can interactively modify the projected coordinates of inputs on the workspace using our designed tools, then the modified information will be fed back to the network to fine-tune it, which in turn affects the network's classification results, thereby improving the accuracy of network classification." @default.
- W4285604194 created "2022-07-16" @default.
- W4285604194 creator A5018306260 @default.
- W4285604194 creator A5045630658 @default.
- W4285604194 creator A5049321721 @default.
- W4285604194 creator A5088980930 @default.
- W4285604194 date "2022-07-01" @default.
- W4285604194 modified "2023-10-18" @default.
- W4285604194 title "Fine-tuning Deep Neural Networks by Interactively Refining the 2D Latent Space of Ambiguous Images" @default.
- W4285604194 doi "https://doi.org/10.24963/ijcai.2022/857" @default.
- W4285604194 hasPublicationYear "2022" @default.
- W4285604194 type Work @default.
- W4285604194 citedByCount "0" @default.
- W4285604194 crossrefType "proceedings-article" @default.
- W4285604194 hasAuthorship W4285604194A5018306260 @default.
- W4285604194 hasAuthorship W4285604194A5045630658 @default.
- W4285604194 hasAuthorship W4285604194A5049321721 @default.
- W4285604194 hasAuthorship W4285604194A5088980930 @default.
- W4285604194 hasBestOaLocation W42856041941 @default.
- W4285604194 hasConcept C111919701 @default.
- W4285604194 hasConcept C119857082 @default.
- W4285604194 hasConcept C153180895 @default.
- W4285604194 hasConcept C154945302 @default.
- W4285604194 hasConcept C2776502983 @default.
- W4285604194 hasConcept C2778572836 @default.
- W4285604194 hasConcept C2984842247 @default.
- W4285604194 hasConcept C31972630 @default.
- W4285604194 hasConcept C41008148 @default.
- W4285604194 hasConcept C50644808 @default.
- W4285604194 hasConcept C58581272 @default.
- W4285604194 hasConcept C90509273 @default.
- W4285604194 hasConceptScore W4285604194C111919701 @default.
- W4285604194 hasConceptScore W4285604194C119857082 @default.
- W4285604194 hasConceptScore W4285604194C153180895 @default.
- W4285604194 hasConceptScore W4285604194C154945302 @default.
- W4285604194 hasConceptScore W4285604194C2776502983 @default.
- W4285604194 hasConceptScore W4285604194C2778572836 @default.
- W4285604194 hasConceptScore W4285604194C2984842247 @default.
- W4285604194 hasConceptScore W4285604194C31972630 @default.
- W4285604194 hasConceptScore W4285604194C41008148 @default.
- W4285604194 hasConceptScore W4285604194C50644808 @default.
- W4285604194 hasConceptScore W4285604194C58581272 @default.
- W4285604194 hasConceptScore W4285604194C90509273 @default.
- W4285604194 hasLocation W42856041941 @default.
- W4285604194 hasOpenAccess W4285604194 @default.
- W4285604194 hasPrimaryLocation W42856041941 @default.
- W4285604194 hasRelatedWork W1910101490 @default.
- W4285604194 hasRelatedWork W1969449762 @default.
- W4285604194 hasRelatedWork W1977373830 @default.
- W4285604194 hasRelatedWork W1987421842 @default.
- W4285604194 hasRelatedWork W2016398835 @default.
- W4285604194 hasRelatedWork W2121179941 @default.
- W4285604194 hasRelatedWork W2168146018 @default.
- W4285604194 hasRelatedWork W3185696992 @default.
- W4285604194 hasRelatedWork W3192344083 @default.
- W4285604194 hasRelatedWork W4366330678 @default.
- W4285604194 isParatext "false" @default.
- W4285604194 isRetracted "false" @default.
- W4285604194 workType "article" @default.