Matches in SemOpenAlex for { <https://semopenalex.org/work/W3159641505> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W3159641505 endingPage "1102" @default.
- W3159641505 startingPage "1102" @default.
- W3159641505 abstract "In order to meet the real-time requirements of the autonomous driving system, the existing method directly up-samples the encoder’s output feature map to pixel-wise prediction, thus neglecting the importance of the decoder for the prediction of detail features. In order to solve this problem, this paper proposes a general lane detection framework based on object feature distillation. Firstly, a decoder with strong feature prediction ability is added to the network using direct up-sampling method. Then, in the network training stage, the prediction results generated by the decoder are regarded as soft targets through knowledge distillation technology, so that the directly up-samples branch can learn more detailed lane information and have a strong feature prediction ability for the decoder. Finally, in the stage of network inference, we only need to use the direct up-sampling branch instead of the forward calculation of the decoder, so compared with the existing model, it can improve the lane detection performance without additional cost. In order to verify the effectiveness of this framework, it is applied to many mainstream lane segmentation methods such as SCNN, DeepLabv1, ResNet, etc. Experimental results show that, under the condition of no additional complexity, the proposed method can obtain higher F1Measure on CuLane dataset." @default.
- W3159641505 created "2021-05-10" @default.
- W3159641505 creator A5050093885 @default.
- W3159641505 creator A5061908912 @default.
- W3159641505 date "2021-05-08" @default.
- W3159641505 modified "2023-10-06" @default.
- W3159641505 title "Lane Line Detection Based on Object Feature Distillation" @default.
- W3159641505 cites W1573510622 @default.
- W3159641505 cites W1829670322 @default.
- W3159641505 cites W2006244290 @default.
- W3159641505 cites W2077709713 @default.
- W3159641505 cites W2152422345 @default.
- W3159641505 cites W2159132531 @default.
- W3159641505 cites W2412782625 @default.
- W3159641505 cites W2745410201 @default.
- W3159641505 cites W2801378207 @default.
- W3159641505 cites W2963881378 @default.
- W3159641505 cites W3081307049 @default.
- W3159641505 cites W3114666952 @default.
- W3159641505 cites W3216042775 @default.
- W3159641505 doi "https://doi.org/10.3390/electronics10091102" @default.
- W3159641505 hasPublicationYear "2021" @default.
- W3159641505 type Work @default.
- W3159641505 sameAs 3159641505 @default.
- W3159641505 citedByCount "20" @default.
- W3159641505 countsByYear W31596415052021 @default.
- W3159641505 countsByYear W31596415052022 @default.
- W3159641505 countsByYear W31596415052023 @default.
- W3159641505 crossrefType "journal-article" @default.
- W3159641505 hasAuthorship W3159641505A5050093885 @default.
- W3159641505 hasAuthorship W3159641505A5061908912 @default.
- W3159641505 hasBestOaLocation W31596415051 @default.
- W3159641505 hasConcept C106131492 @default.
- W3159641505 hasConcept C111919701 @default.
- W3159641505 hasConcept C118505674 @default.
- W3159641505 hasConcept C124101348 @default.
- W3159641505 hasConcept C138885662 @default.
- W3159641505 hasConcept C140779682 @default.
- W3159641505 hasConcept C153180895 @default.
- W3159641505 hasConcept C154945302 @default.
- W3159641505 hasConcept C178790620 @default.
- W3159641505 hasConcept C185592680 @default.
- W3159641505 hasConcept C204030448 @default.
- W3159641505 hasConcept C2776151529 @default.
- W3159641505 hasConcept C2776214188 @default.
- W3159641505 hasConcept C2776401178 @default.
- W3159641505 hasConcept C31972630 @default.
- W3159641505 hasConcept C41008148 @default.
- W3159641505 hasConcept C41895202 @default.
- W3159641505 hasConcept C52622490 @default.
- W3159641505 hasConcept C89600930 @default.
- W3159641505 hasConceptScore W3159641505C106131492 @default.
- W3159641505 hasConceptScore W3159641505C111919701 @default.
- W3159641505 hasConceptScore W3159641505C118505674 @default.
- W3159641505 hasConceptScore W3159641505C124101348 @default.
- W3159641505 hasConceptScore W3159641505C138885662 @default.
- W3159641505 hasConceptScore W3159641505C140779682 @default.
- W3159641505 hasConceptScore W3159641505C153180895 @default.
- W3159641505 hasConceptScore W3159641505C154945302 @default.
- W3159641505 hasConceptScore W3159641505C178790620 @default.
- W3159641505 hasConceptScore W3159641505C185592680 @default.
- W3159641505 hasConceptScore W3159641505C204030448 @default.
- W3159641505 hasConceptScore W3159641505C2776151529 @default.
- W3159641505 hasConceptScore W3159641505C2776214188 @default.
- W3159641505 hasConceptScore W3159641505C2776401178 @default.
- W3159641505 hasConceptScore W3159641505C31972630 @default.
- W3159641505 hasConceptScore W3159641505C41008148 @default.
- W3159641505 hasConceptScore W3159641505C41895202 @default.
- W3159641505 hasConceptScore W3159641505C52622490 @default.
- W3159641505 hasConceptScore W3159641505C89600930 @default.
- W3159641505 hasIssue "9" @default.
- W3159641505 hasLocation W31596415051 @default.
- W3159641505 hasOpenAccess W3159641505 @default.
- W3159641505 hasPrimaryLocation W31596415051 @default.
- W3159641505 hasRelatedWork W2016461833 @default.
- W3159641505 hasRelatedWork W2059299633 @default.
- W3159641505 hasRelatedWork W2144059113 @default.
- W3159641505 hasRelatedWork W2146076056 @default.
- W3159641505 hasRelatedWork W2546942002 @default.
- W3159641505 hasRelatedWork W2734888972 @default.
- W3159641505 hasRelatedWork W2811390910 @default.
- W3159641505 hasRelatedWork W3003836766 @default.
- W3159641505 hasRelatedWork W3195533956 @default.
- W3159641505 hasRelatedWork W3197541072 @default.
- W3159641505 hasVolume "10" @default.
- W3159641505 isParatext "false" @default.
- W3159641505 isRetracted "false" @default.
- W3159641505 magId "3159641505" @default.
- W3159641505 workType "article" @default.