Matches in SemOpenAlex for { <https://semopenalex.org/work/W3197308906> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W3197308906 abstract "In recent years, deep convolutional neural networks have made significant advances in pathology image segmentation. However, pathology image segmentation encounters with a dilemma in which the higher-performance networks generally require more computational resources and storage. This phenomenon limits the employment of high-accuracy networks in real scenes due to the inherent high-resolution of pathological images. To tackle this problem, we propose CoCo DistillNet, a novel Cross-layer Correlation (CoCo) knowledge distillation network for pathological gastric cancer segmentation. Knowledge distillation, a general technique which aims at improving the performance of a compact network through knowledge transfer from a cumbersome network. Concretely, our CoCo DistillNet models the correlations of channel-mixed spatial similarity between different layers and then transfers this knowledge from a pre-trained cumbersome teacher network to a non-trained compact student network. In addition, we also utilize the adversarial learning strategy to further prompt the distilling procedure which is called Adversarial Distillation (AD). Furthermore, to stabilize our training procedure, we make the use of the unsupervised Paraphraser Module (PM) to boost the knowledge paraphrase in the teacher network. As a result, extensive experiments conducted on the Gastric Cancer Segmentation Dataset demonstrate the prominent ability of CoCo DistillNet which achieves state-of-the-art performance." @default.
- W3197308906 created "2021-09-13" @default.
- W3197308906 creator A5049289977 @default.
- W3197308906 creator A5084960489 @default.
- W3197308906 date "2021-08-27" @default.
- W3197308906 modified "2023-09-27" @default.
- W3197308906 title "CoCo DistillNet: a Cross-layer Correlation Distillation Network for Pathological Gastric Cancer Segmentation" @default.
- W3197308906 cites W1690739335 @default.
- W3197308906 cites W1821462560 @default.
- W3197308906 cites W1901129140 @default.
- W3197308906 cites W2114766824 @default.
- W3197308906 cites W2233116163 @default.
- W3197308906 cites W2267635276 @default.
- W3197308906 cites W2419448466 @default.
- W3197308906 cites W2610180723 @default.
- W3197308906 cites W2739879705 @default.
- W3197308906 cites W2762439315 @default.
- W3197308906 cites W2783538964 @default.
- W3197308906 cites W2786945063 @default.
- W3197308906 cites W2793444752 @default.
- W3197308906 cites W2796573347 @default.
- W3197308906 cites W2946121192 @default.
- W3197308906 cites W2949829435 @default.
- W3197308906 cites W2952787292 @default.
- W3197308906 cites W2954054736 @default.
- W3197308906 cites W2963163009 @default.
- W3197308906 cites W2963674932 @default.
- W3197308906 cites W2964157630 @default.
- W3197308906 cites W2982242214 @default.
- W3197308906 cites W2982805640 @default.
- W3197308906 cites W2986015886 @default.
- W3197308906 cites W2998544007 @default.
- W3197308906 cites W2999803881 @default.
- W3197308906 cites W3034879391 @default.
- W3197308906 cites W3082947597 @default.
- W3197308906 cites W3089571734 @default.
- W3197308906 cites W3092580847 @default.
- W3197308906 cites W3097836310 @default.
- W3197308906 cites W3105676814 @default.
- W3197308906 cites W3108855944 @default.
- W3197308906 cites W3190905285 @default.
- W3197308906 doi "https://doi.org/10.48550/arxiv.2108.12173" @default.
- W3197308906 hasPublicationYear "2021" @default.
- W3197308906 type Work @default.
- W3197308906 sameAs 3197308906 @default.
- W3197308906 citedByCount "0" @default.
- W3197308906 crossrefType "posted-content" @default.
- W3197308906 hasAuthorship W3197308906A5049289977 @default.
- W3197308906 hasAuthorship W3197308906A5084960489 @default.
- W3197308906 hasBestOaLocation W31973089061 @default.
- W3197308906 hasConcept C108583219 @default.
- W3197308906 hasConcept C119857082 @default.
- W3197308906 hasConcept C153180895 @default.
- W3197308906 hasConcept C154945302 @default.
- W3197308906 hasConcept C21780288 @default.
- W3197308906 hasConcept C41008148 @default.
- W3197308906 hasConcept C81363708 @default.
- W3197308906 hasConcept C89600930 @default.
- W3197308906 hasConceptScore W3197308906C108583219 @default.
- W3197308906 hasConceptScore W3197308906C119857082 @default.
- W3197308906 hasConceptScore W3197308906C153180895 @default.
- W3197308906 hasConceptScore W3197308906C154945302 @default.
- W3197308906 hasConceptScore W3197308906C21780288 @default.
- W3197308906 hasConceptScore W3197308906C41008148 @default.
- W3197308906 hasConceptScore W3197308906C81363708 @default.
- W3197308906 hasConceptScore W3197308906C89600930 @default.
- W3197308906 hasLocation W31973089061 @default.
- W3197308906 hasOpenAccess W3197308906 @default.
- W3197308906 hasPrimaryLocation W31973089061 @default.
- W3197308906 hasRelatedWork W2337926734 @default.
- W3197308906 hasRelatedWork W2738221750 @default.
- W3197308906 hasRelatedWork W3102253946 @default.
- W3197308906 hasRelatedWork W3144574764 @default.
- W3197308906 hasRelatedWork W3156786002 @default.
- W3197308906 hasRelatedWork W4293211451 @default.
- W3197308906 hasRelatedWork W4308191152 @default.
- W3197308906 hasRelatedWork W4311257506 @default.
- W3197308906 hasRelatedWork W4381487685 @default.
- W3197308906 hasRelatedWork W564581980 @default.
- W3197308906 isParatext "false" @default.
- W3197308906 isRetracted "false" @default.
- W3197308906 magId "3197308906" @default.
- W3197308906 workType "article" @default.