Matches in SemOpenAlex for { <https://semopenalex.org/work/W2963948425> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W2963948425 abstract "With pervasive applications of medical imaging in health-care, biomedical image segmentation plays a central role in quantitative analysis, clinical diagno- sis, and medical intervention. Since manual anno- tation su ers limited reproducibility, arduous e orts, and excessive time, automatic segmentation is desired to process increasingly larger scale histopathological data. Recently, deep neural networks (DNNs), par- ticularly fully convolutional networks (FCNs), have been widely applied to biomedical image segmenta- tion, attaining much improved performance. At the same time, quantization of DNNs has become an ac- tive research topic, which aims to represent weights with less memory (precision) to considerably reduce memory and computation requirements of DNNs while maintaining acceptable accuracy. In this paper, we apply quantization techniques to FCNs for accurate biomedical image segmentation. Unlike existing litera- ture on quantization which primarily targets memory and computation complexity reduction, we apply quan- tization as a method to reduce over tting in FCNs for better accuracy. Speci cally, we focus on a state-of- the-art segmentation framework, suggestive annotation [22], which judiciously extracts representative annota- tion samples from the original training dataset, obtain- ing an e ective small-sized balanced training dataset. We develop two new quantization processes for this framework: (1) suggestive annotation with quantiza- tion for highly representative training samples, and (2) network training with quantization for high accuracy. Extensive experiments on the MICCAI Gland dataset show that both quantization processes can improve the segmentation performance, and our proposed method exceeds the current state-of-the-art performance by up to 1%. In addition, our method has a reduction of up to 6.4x on memory usage." @default.
- W2963948425 created "2019-07-30" @default.
- W2963948425 creator A5000141831 @default.
- W2963948425 creator A5011459062 @default.
- W2963948425 creator A5024585813 @default.
- W2963948425 creator A5047868177 @default.
- W2963948425 creator A5049335103 @default.
- W2963948425 creator A5059658485 @default.
- W2963948425 creator A5071529609 @default.
- W2963948425 date "2018-06-01" @default.
- W2963948425 modified "2023-10-12" @default.
- W2963948425 title "Quantization of Fully Convolutional Networks for Accurate Biomedical Image Segmentation" @default.
- W2963948425 cites W1950315773 @default.
- W2963948425 cites W2011966237 @default.
- W2963948425 cites W2108598243 @default.
- W2963948425 cites W2128252595 @default.
- W2963948425 cites W2134647348 @default.
- W2963948425 cites W2156398782 @default.
- W2963948425 cites W2288892845 @default.
- W2963948425 cites W2799898080 @default.
- W2963948425 cites W2963803174 @default.
- W2963948425 cites W4237832974 @default.
- W2963948425 doi "https://doi.org/10.1109/cvpr.2018.00866" @default.
- W2963948425 hasPublicationYear "2018" @default.
- W2963948425 type Work @default.
- W2963948425 sameAs 2963948425 @default.
- W2963948425 citedByCount "81" @default.
- W2963948425 countsByYear W29639484252018 @default.
- W2963948425 countsByYear W29639484252019 @default.
- W2963948425 countsByYear W29639484252020 @default.
- W2963948425 countsByYear W29639484252021 @default.
- W2963948425 countsByYear W29639484252022 @default.
- W2963948425 countsByYear W29639484252023 @default.
- W2963948425 crossrefType "proceedings-article" @default.
- W2963948425 hasAuthorship W2963948425A5000141831 @default.
- W2963948425 hasAuthorship W2963948425A5011459062 @default.
- W2963948425 hasAuthorship W2963948425A5024585813 @default.
- W2963948425 hasAuthorship W2963948425A5047868177 @default.
- W2963948425 hasAuthorship W2963948425A5049335103 @default.
- W2963948425 hasAuthorship W2963948425A5059658485 @default.
- W2963948425 hasAuthorship W2963948425A5071529609 @default.
- W2963948425 hasBestOaLocation W29639484252 @default.
- W2963948425 hasConcept C11413529 @default.
- W2963948425 hasConcept C119857082 @default.
- W2963948425 hasConcept C124504099 @default.
- W2963948425 hasConcept C153180895 @default.
- W2963948425 hasConcept C154945302 @default.
- W2963948425 hasConcept C2776321320 @default.
- W2963948425 hasConcept C28855332 @default.
- W2963948425 hasConcept C31972630 @default.
- W2963948425 hasConcept C41008148 @default.
- W2963948425 hasConcept C45374587 @default.
- W2963948425 hasConcept C81363708 @default.
- W2963948425 hasConcept C89600930 @default.
- W2963948425 hasConceptScore W2963948425C11413529 @default.
- W2963948425 hasConceptScore W2963948425C119857082 @default.
- W2963948425 hasConceptScore W2963948425C124504099 @default.
- W2963948425 hasConceptScore W2963948425C153180895 @default.
- W2963948425 hasConceptScore W2963948425C154945302 @default.
- W2963948425 hasConceptScore W2963948425C2776321320 @default.
- W2963948425 hasConceptScore W2963948425C28855332 @default.
- W2963948425 hasConceptScore W2963948425C31972630 @default.
- W2963948425 hasConceptScore W2963948425C41008148 @default.
- W2963948425 hasConceptScore W2963948425C45374587 @default.
- W2963948425 hasConceptScore W2963948425C81363708 @default.
- W2963948425 hasConceptScore W2963948425C89600930 @default.
- W2963948425 hasLocation W29639484251 @default.
- W2963948425 hasLocation W29639484252 @default.
- W2963948425 hasOpenAccess W2963948425 @default.
- W2963948425 hasPrimaryLocation W29639484251 @default.
- W2963948425 hasRelatedWork W2005476934 @default.
- W2963948425 hasRelatedWork W2769435486 @default.
- W2963948425 hasRelatedWork W2893610713 @default.
- W2963948425 hasRelatedWork W2897195263 @default.
- W2963948425 hasRelatedWork W2979932740 @default.
- W2963948425 hasRelatedWork W3085581207 @default.
- W2963948425 hasRelatedWork W3093612317 @default.
- W2963948425 hasRelatedWork W3095523211 @default.
- W2963948425 hasRelatedWork W4200528772 @default.
- W2963948425 hasRelatedWork W4287776258 @default.
- W2963948425 isParatext "false" @default.
- W2963948425 isRetracted "false" @default.
- W2963948425 magId "2963948425" @default.
- W2963948425 workType "article" @default.