Matches in SemOpenAlex for { <https://semopenalex.org/work/W3200572726> ?p ?o ?g. }
- W3200572726 abstract "Diabetic retinopathy is one of the leading causes of blindness. However, no specific symptoms of early DR lead to a delayed diagnosis, which results in disease progression in patients. To determine the disease severity levels, ophthalmologists need to focus on the discriminative parts of the retinal images. In recent years, deep learning has achieved great success in medical image analysis. However, most works directly employ algorithms based on convolutional neural networks (CNNs), which ignore the fact that the difference among classes is subtle and gradual. Hence, we consider automatic image grading of DR as a fine-grained classification task, and construct a bilinear model to identify the pathologically discriminative areas. In order to leverage the ordinal information among classes, we put the soft labels with ordinal information among classes into the loss function rather than the most commonly used one-hot labels for the diabetic retinopathy classification. In addition, other than only using a categorical loss to train our network, we also introduce the metric loss to learn a more discriminative feature space which is beneficial to locate the finer discriminative lesion parts. Experimental results demonstrate the superior performance of the proposed method on publicly available IDRiD, DeepDRiD and FGADR datasets." @default.
- W3200572726 created "2021-09-27" @default.
- W3200572726 creator A5007681737 @default.
- W3200572726 creator A5016129592 @default.
- W3200572726 creator A5017921159 @default.
- W3200572726 creator A5068602599 @default.
- W3200572726 creator A5086702173 @default.
- W3200572726 date "2021-07-18" @default.
- W3200572726 modified "2023-10-18" @default.
- W3200572726 title "Learning Discriminative Representations for Fine-Grained Diabetic Retinopathy Grading" @default.
- W3200572726 cites W1414145206 @default.
- W3200572726 cites W1905153633 @default.
- W3200572726 cites W1966206262 @default.
- W3200572726 cites W2104657103 @default.
- W3200572726 cites W2138011018 @default.
- W3200572726 cites W2164777277 @default.
- W3200572726 cites W2170021941 @default.
- W3200572726 cites W2183341477 @default.
- W3200572726 cites W2194775991 @default.
- W3200572726 cites W2239239723 @default.
- W3200572726 cites W2440214111 @default.
- W3200572726 cites W2502390809 @default.
- W3200572726 cites W2557738935 @default.
- W3200572726 cites W2598442119 @default.
- W3200572726 cites W2626629100 @default.
- W3200572726 cites W2798365843 @default.
- W3200572726 cites W2810170988 @default.
- W3200572726 cites W2889469641 @default.
- W3200572726 cites W2891951760 @default.
- W3200572726 cites W2949208911 @default.
- W3200572726 cites W2962858109 @default.
- W3200572726 cites W2963351448 @default.
- W3200572726 cites W2963446712 @default.
- W3200572726 cites W2963813458 @default.
- W3200572726 cites W2977650145 @default.
- W3200572726 cites W2991234496 @default.
- W3200572726 cites W3097760447 @default.
- W3200572726 cites W3098558149 @default.
- W3200572726 cites W3108870912 @default.
- W3200572726 doi "https://doi.org/10.1109/ijcnn52387.2021.9533344" @default.
- W3200572726 hasPublicationYear "2021" @default.
- W3200572726 type Work @default.
- W3200572726 sameAs 3200572726 @default.
- W3200572726 citedByCount "4" @default.
- W3200572726 countsByYear W32005727262022 @default.
- W3200572726 countsByYear W32005727262023 @default.
- W3200572726 crossrefType "proceedings-article" @default.
- W3200572726 hasAuthorship W3200572726A5007681737 @default.
- W3200572726 hasAuthorship W3200572726A5016129592 @default.
- W3200572726 hasAuthorship W3200572726A5017921159 @default.
- W3200572726 hasAuthorship W3200572726A5068602599 @default.
- W3200572726 hasAuthorship W3200572726A5086702173 @default.
- W3200572726 hasBestOaLocation W32005727262 @default.
- W3200572726 hasConcept C108583219 @default.
- W3200572726 hasConcept C115961682 @default.
- W3200572726 hasConcept C119857082 @default.
- W3200572726 hasConcept C127413603 @default.
- W3200572726 hasConcept C134018914 @default.
- W3200572726 hasConcept C147176958 @default.
- W3200572726 hasConcept C153083717 @default.
- W3200572726 hasConcept C153180895 @default.
- W3200572726 hasConcept C154945302 @default.
- W3200572726 hasConcept C2777286243 @default.
- W3200572726 hasConcept C2779829184 @default.
- W3200572726 hasConcept C41008148 @default.
- W3200572726 hasConcept C555293320 @default.
- W3200572726 hasConcept C71924100 @default.
- W3200572726 hasConcept C75294576 @default.
- W3200572726 hasConcept C81363708 @default.
- W3200572726 hasConcept C97931131 @default.
- W3200572726 hasConceptScore W3200572726C108583219 @default.
- W3200572726 hasConceptScore W3200572726C115961682 @default.
- W3200572726 hasConceptScore W3200572726C119857082 @default.
- W3200572726 hasConceptScore W3200572726C127413603 @default.
- W3200572726 hasConceptScore W3200572726C134018914 @default.
- W3200572726 hasConceptScore W3200572726C147176958 @default.
- W3200572726 hasConceptScore W3200572726C153083717 @default.
- W3200572726 hasConceptScore W3200572726C153180895 @default.
- W3200572726 hasConceptScore W3200572726C154945302 @default.
- W3200572726 hasConceptScore W3200572726C2777286243 @default.
- W3200572726 hasConceptScore W3200572726C2779829184 @default.
- W3200572726 hasConceptScore W3200572726C41008148 @default.
- W3200572726 hasConceptScore W3200572726C555293320 @default.
- W3200572726 hasConceptScore W3200572726C71924100 @default.
- W3200572726 hasConceptScore W3200572726C75294576 @default.
- W3200572726 hasConceptScore W3200572726C81363708 @default.
- W3200572726 hasConceptScore W3200572726C97931131 @default.
- W3200572726 hasLocation W32005727261 @default.
- W3200572726 hasLocation W32005727262 @default.
- W3200572726 hasOpenAccess W3200572726 @default.
- W3200572726 hasPrimaryLocation W32005727261 @default.
- W3200572726 hasRelatedWork W1482209366 @default.
- W3200572726 hasRelatedWork W2110523656 @default.
- W3200572726 hasRelatedWork W2153315159 @default.
- W3200572726 hasRelatedWork W2521627374 @default.
- W3200572726 hasRelatedWork W259157601 @default.
- W3200572726 hasRelatedWork W2761785940 @default.
- W3200572726 hasRelatedWork W2965546495 @default.
- W3200572726 hasRelatedWork W2971377935 @default.
- W3200572726 hasRelatedWork W3103844505 @default.