FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3201465887> ?p ?o ?g. }

• W3201465887 abstract "There is an emerging sense that the vulnerability of Image Convolutional Neural Networks (CNN), i.e., sensitivity to image corruptions, perturbations, and adversarial attacks, is connected with Texture Bias. This relative lack of Shape Bias is also responsible for poor performance in Domain Generalization (DG). The inclusion of a role of shape alleviates these vulnerabilities and some approaches have achieved this by training on negative images, images endowed with edge maps, or images with conflicting shape and texture information. This paper advocates an explicit and complete representation of shape using a classical computer vision approach, namely, representing the shape content of an image with the shock graph of its contour map. The resulting graph and its descriptor is a complete representation of contour content and is classified using recent Graph Neural Network (GNN) methods. The experimental results on three domain shift datasets, Colored MNIST, PACS, and VLCS demonstrate that even without using appearance the shape-based approach exceeds classical Image CNN based methods in domain generalization." @default.
• W3201465887 created "2021-09-27" @default.
• W3201465887 creator A5000034602 @default.
• W3201465887 creator A5055026354 @default.
• W3201465887 creator A5083461641 @default.
• W3201465887 date "2021-10-01" @default.
• W3201465887 modified "2023-09-27" @default.
• W3201465887 title "Shape-Biased Domain Generalization via Shock Graph Embeddings" @default.
• W3201465887 cites W1522089931 @default.
• W3201465887 cites W1920962657 @default.
• W3201465887 cites W1976047850 @default.
• W3201465887 cites W1982522767 @default.
• W3201465887 cites W2028785429 @default.
• W3201465887 cites W2037227137 @default.
• W3201465887 cites W2055237367 @default.
• W3201465887 cites W2078267645 @default.
• W3201465887 cites W2088114053 @default.
• W3201465887 cites W2096316207 @default.
• W3201465887 cites W2100968369 @default.
• W3201465887 cites W2110764733 @default.
• W3201465887 cites W2114766304 @default.
• W3201465887 cites W2125310690 @default.
• W3201465887 cites W2140598250 @default.
• W3201465887 cites W2155904486 @default.
• W3201465887 cites W2156406284 @default.
• W3201465887 cites W2167366427 @default.
• W3201465887 cites W2176287621 @default.
• W3201465887 cites W2202734424 @default.
• W3201465887 cites W2604709832 @default.
• W3201465887 cites W2763549966 @default.
• W3201465887 cites W2798658180 @default.
• W3201465887 cites W2903867357 @default.
• W3201465887 cites W2919115771 @default.
• W3201465887 cites W2958360136 @default.
• W3201465887 cites W2962940674 @default.
• W3201465887 cites W2963118547 @default.
• W3201465887 cites W2963857521 @default.
• W3201465887 cites W2981368934 @default.
• W3201465887 cites W2991391304 @default.
• W3201465887 cites W3025069833 @default.
• W3201465887 cites W3034373371 @default.
• W3201465887 cites W3035115087 @default.
• W3201465887 cites W3035131301 @default.
• W3201465887 cites W45101619 @default.
• W3201465887 cites W1991140842 @default.
• W3201465887 cites W281061080 @default.
• W3201465887 doi "https://doi.org/10.1109/iccv48922.2021.00135" @default.
• W3201465887 hasPublicationYear "2021" @default.
• W3201465887 type Work @default.
• W3201465887 sameAs 3201465887 @default.
• W3201465887 citedByCount "5" @default.
• W3201465887 countsByYear W32014658872022 @default.
• W3201465887 countsByYear W32014658872023 @default.
• W3201465887 crossrefType "proceedings-article" @default.
• W3201465887 hasAuthorship W3201465887A5000034602 @default.
• W3201465887 hasAuthorship W3201465887A5055026354 @default.
• W3201465887 hasAuthorship W3201465887A5083461641 @default.
• W3201465887 hasBestOaLocation W32014658872 @default.
• W3201465887 hasConcept C115961682 @default.
• W3201465887 hasConcept C132525143 @default.
• W3201465887 hasConcept C134306372 @default.
• W3201465887 hasConcept C153180895 @default.
• W3201465887 hasConcept C154945302 @default.
• W3201465887 hasConcept C177148314 @default.
• W3201465887 hasConcept C17744445 @default.
• W3201465887 hasConcept C190502265 @default.
• W3201465887 hasConcept C199539241 @default.
• W3201465887 hasConcept C2776359362 @default.
• W3201465887 hasConcept C31972630 @default.
• W3201465887 hasConcept C33923547 @default.
• W3201465887 hasConcept C41008148 @default.
• W3201465887 hasConcept C50644808 @default.
• W3201465887 hasConcept C80444323 @default.
• W3201465887 hasConcept C81363708 @default.
• W3201465887 hasConcept C94625758 @default.
• W3201465887 hasConceptScore W3201465887C115961682 @default.
• W3201465887 hasConceptScore W3201465887C132525143 @default.
• W3201465887 hasConceptScore W3201465887C134306372 @default.
• W3201465887 hasConceptScore W3201465887C153180895 @default.
• W3201465887 hasConceptScore W3201465887C154945302 @default.
• W3201465887 hasConceptScore W3201465887C177148314 @default.
• W3201465887 hasConceptScore W3201465887C17744445 @default.
• W3201465887 hasConceptScore W3201465887C190502265 @default.
• W3201465887 hasConceptScore W3201465887C199539241 @default.
• W3201465887 hasConceptScore W3201465887C2776359362 @default.
• W3201465887 hasConceptScore W3201465887C31972630 @default.
• W3201465887 hasConceptScore W3201465887C33923547 @default.
• W3201465887 hasConceptScore W3201465887C41008148 @default.
• W3201465887 hasConceptScore W3201465887C50644808 @default.
• W3201465887 hasConceptScore W3201465887C80444323 @default.
• W3201465887 hasConceptScore W3201465887C81363708 @default.
• W3201465887 hasConceptScore W3201465887C94625758 @default.
• W3201465887 hasLocation W32014658871 @default.
• W3201465887 hasLocation W32014658872 @default.
• W3201465887 hasOpenAccess W3201465887 @default.
• W3201465887 hasPrimaryLocation W32014658871 @default.
• W3201465887 hasRelatedWork W2771907641 @default.
• W3201465887 hasRelatedWork W2810865670 @default.
• W3201465887 hasRelatedWork W2891963476 @default.
• W3201465887 hasRelatedWork W2908808515 @default.

• next