Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204725823> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W3204725823 endingPage "238" @default.
- W3204725823 startingPage "229" @default.
- W3204725823 abstract "The recurrent mechanism has recently been introduced into U-Net in various medical image segmentation tasks. Existing studies have focused on promoting network recursion via reusing building blocks. Although network parameters could be greatly saved, computational costs still increase inevitably in accordance with the pre-set iteration time. In this work, we study a multi-scale upgrade of a bi-directional skip connected network and then automatically discover an efficient architecture by a novel two-phase Neural Architecture Search (NAS) algorithm, namely BiX-NAS. Our proposed method reduces the network computational cost by sifting out ineffective multi-scale features at different levels and iterations. We evaluate BiX-NAS on two segmentation tasks using three different medical image datasets, and the experimental results show that our BiX-NAS searched architecture achieves the state-of-the-art performance with significantly lower computational cost. Our project page is available at: https://bionets.github.io." @default.
- W3204725823 created "2021-10-11" @default.
- W3204725823 creator A5027686620 @default.
- W3204725823 creator A5040523461 @default.
- W3204725823 creator A5041567418 @default.
- W3204725823 creator A5060016795 @default.
- W3204725823 creator A5076343081 @default.
- W3204725823 creator A5076697411 @default.
- W3204725823 creator A5080719369 @default.
- W3204725823 date "2021-01-01" @default.
- W3204725823 modified "2023-09-27" @default.
- W3204725823 title "BiX-NAS: Searching Efficient Bi-directional Architecture for Medical Image Segmentation" @default.
- W3204725823 cites W1901129140 @default.
- W3204725823 cites W2592905743 @default.
- W3204725823 cites W2884436604 @default.
- W3204725823 cites W2885343725 @default.
- W3204725823 cites W2905338897 @default.
- W3204725823 cites W2927980542 @default.
- W3204725823 cites W2963136578 @default.
- W3204725823 cites W2974825848 @default.
- W3204725823 cites W2982182858 @default.
- W3204725823 cites W3002569343 @default.
- W3204725823 cites W3015788359 @default.
- W3204725823 cites W3034357629 @default.
- W3204725823 cites W3092052974 @default.
- W3204725823 cites W3092618738 @default.
- W3204725823 cites W3096533519 @default.
- W3204725823 doi "https://doi.org/10.1007/978-3-030-87193-2_22" @default.
- W3204725823 hasPublicationYear "2021" @default.
- W3204725823 type Work @default.
- W3204725823 sameAs 3204725823 @default.
- W3204725823 citedByCount "10" @default.
- W3204725823 countsByYear W32047258232021 @default.
- W3204725823 countsByYear W32047258232022 @default.
- W3204725823 countsByYear W32047258232023 @default.
- W3204725823 crossrefType "book-chapter" @default.
- W3204725823 hasAuthorship W3204725823A5027686620 @default.
- W3204725823 hasAuthorship W3204725823A5040523461 @default.
- W3204725823 hasAuthorship W3204725823A5041567418 @default.
- W3204725823 hasAuthorship W3204725823A5060016795 @default.
- W3204725823 hasAuthorship W3204725823A5076343081 @default.
- W3204725823 hasAuthorship W3204725823A5076697411 @default.
- W3204725823 hasAuthorship W3204725823A5080719369 @default.
- W3204725823 hasBestOaLocation W32047258232 @default.
- W3204725823 hasConcept C115961682 @default.
- W3204725823 hasConcept C121684516 @default.
- W3204725823 hasConcept C123657996 @default.
- W3204725823 hasConcept C154945302 @default.
- W3204725823 hasConcept C166957645 @default.
- W3204725823 hasConcept C205649164 @default.
- W3204725823 hasConcept C31972630 @default.
- W3204725823 hasConcept C41008148 @default.
- W3204725823 hasConcept C89600930 @default.
- W3204725823 hasConceptScore W3204725823C115961682 @default.
- W3204725823 hasConceptScore W3204725823C121684516 @default.
- W3204725823 hasConceptScore W3204725823C123657996 @default.
- W3204725823 hasConceptScore W3204725823C154945302 @default.
- W3204725823 hasConceptScore W3204725823C166957645 @default.
- W3204725823 hasConceptScore W3204725823C205649164 @default.
- W3204725823 hasConceptScore W3204725823C31972630 @default.
- W3204725823 hasConceptScore W3204725823C41008148 @default.
- W3204725823 hasConceptScore W3204725823C89600930 @default.
- W3204725823 hasLocation W32047258231 @default.
- W3204725823 hasLocation W32047258232 @default.
- W3204725823 hasOpenAccess W3204725823 @default.
- W3204725823 hasPrimaryLocation W32047258231 @default.
- W3204725823 hasRelatedWork W1669643531 @default.
- W3204725823 hasRelatedWork W2005437358 @default.
- W3204725823 hasRelatedWork W2008656436 @default.
- W3204725823 hasRelatedWork W2023558673 @default.
- W3204725823 hasRelatedWork W2039154422 @default.
- W3204725823 hasRelatedWork W2122581818 @default.
- W3204725823 hasRelatedWork W2134924024 @default.
- W3204725823 hasRelatedWork W2517104666 @default.
- W3204725823 hasRelatedWork W2895616727 @default.
- W3204725823 hasRelatedWork W2182382398 @default.
- W3204725823 isParatext "false" @default.
- W3204725823 isRetracted "false" @default.
- W3204725823 magId "3204725823" @default.
- W3204725823 workType "book-chapter" @default.