Matches in SemOpenAlex for { <https://semopenalex.org/work/W3082775802> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W3082775802 abstract "Feature reuse from earlier layers in neural network hierarchies has been shown to improve the quality of features at a later stage - a concept known as residual learning. In this thesis, we learn effective residual learning methodologies infused with attention mechanisms to observe their effect on different tasks. To this end, we propose 3 architectures across medical image segmentation and 3D point cloud analysis. In FocusNet, we propose an attention based dual branch encoder decoder structure that learns an extremely efficient attention mechanism which achieves state of the art results on the ISIC 2017 skin cancer segmentation dataset. We propose a novel loss enhancement that improves the convergence of FocusNet, performing better than state-of-the-art loss functions such as tversky and focal loss. Evaluations of the architecture proposes two drawbacks which we fix in FocusNetAlpha. Our novel residual group attention block based network forms the backbone of this architecture, learning distinct features with sparse correlations, which is the key reason for its effectiveness. At the time of writing this thesis, FocusNetAlpha outperforms all state-of-the-art convolutional autoencoders with the least parameters and FLOPs compared to them, based on our experiments on the ISIC 2018, DRIVE retinal vessel segmentation and the cell nuclei segmentation dataset. We then shift our attention to 3D point cloud processing where we propose SAWNet, which combines global and local point embeddings infused with attention, to create a spatially aware embedding that outperforms both. We propose a novel method to learn a global feature aggregation for point clouds via a fully differential block that does not need a lot of trainable parameters and gives obvious performance boosts. SAWNet beats state-of-the-art results on ModelNet40 and ShapeNet part segmentation datasets." @default.
- W3082775802 created "2020-09-08" @default.
- W3082775802 creator A5076295200 @default.
- W3082775802 date "2019-11-01" @default.
- W3082775802 modified "2023-09-27" @default.
- W3082775802 title "Models of Visual Attention in Deep Residual CNNs" @default.
- W3082775802 cites W2748788739 @default.
- W3082775802 cites W2963125010 @default.
- W3082775802 cites W2963759070 @default.
- W3082775802 hasPublicationYear "2019" @default.
- W3082775802 type Work @default.
- W3082775802 sameAs 3082775802 @default.
- W3082775802 citedByCount "0" @default.
- W3082775802 crossrefType "dissertation" @default.
- W3082775802 hasAuthorship W3082775802A5076295200 @default.
- W3082775802 hasConcept C108583219 @default.
- W3082775802 hasConcept C111919701 @default.
- W3082775802 hasConcept C11413529 @default.
- W3082775802 hasConcept C118505674 @default.
- W3082775802 hasConcept C131979681 @default.
- W3082775802 hasConcept C138885662 @default.
- W3082775802 hasConcept C153180895 @default.
- W3082775802 hasConcept C154945302 @default.
- W3082775802 hasConcept C155512373 @default.
- W3082775802 hasConcept C173608175 @default.
- W3082775802 hasConcept C2524010 @default.
- W3082775802 hasConcept C2776401178 @default.
- W3082775802 hasConcept C2777210771 @default.
- W3082775802 hasConcept C33923547 @default.
- W3082775802 hasConcept C3826847 @default.
- W3082775802 hasConcept C41008148 @default.
- W3082775802 hasConcept C41608201 @default.
- W3082775802 hasConcept C41895202 @default.
- W3082775802 hasConcept C59404180 @default.
- W3082775802 hasConcept C81363708 @default.
- W3082775802 hasConcept C89600930 @default.
- W3082775802 hasConceptScore W3082775802C108583219 @default.
- W3082775802 hasConceptScore W3082775802C111919701 @default.
- W3082775802 hasConceptScore W3082775802C11413529 @default.
- W3082775802 hasConceptScore W3082775802C118505674 @default.
- W3082775802 hasConceptScore W3082775802C131979681 @default.
- W3082775802 hasConceptScore W3082775802C138885662 @default.
- W3082775802 hasConceptScore W3082775802C153180895 @default.
- W3082775802 hasConceptScore W3082775802C154945302 @default.
- W3082775802 hasConceptScore W3082775802C155512373 @default.
- W3082775802 hasConceptScore W3082775802C173608175 @default.
- W3082775802 hasConceptScore W3082775802C2524010 @default.
- W3082775802 hasConceptScore W3082775802C2776401178 @default.
- W3082775802 hasConceptScore W3082775802C2777210771 @default.
- W3082775802 hasConceptScore W3082775802C33923547 @default.
- W3082775802 hasConceptScore W3082775802C3826847 @default.
- W3082775802 hasConceptScore W3082775802C41008148 @default.
- W3082775802 hasConceptScore W3082775802C41608201 @default.
- W3082775802 hasConceptScore W3082775802C41895202 @default.
- W3082775802 hasConceptScore W3082775802C59404180 @default.
- W3082775802 hasConceptScore W3082775802C81363708 @default.
- W3082775802 hasConceptScore W3082775802C89600930 @default.
- W3082775802 hasLocation W30827758021 @default.
- W3082775802 hasOpenAccess W3082775802 @default.
- W3082775802 hasPrimaryLocation W30827758021 @default.
- W3082775802 hasRelatedWork W2340017589 @default.
- W3082775802 hasRelatedWork W2744404335 @default.
- W3082775802 hasRelatedWork W2760575525 @default.
- W3082775802 hasRelatedWork W2798791651 @default.
- W3082775802 hasRelatedWork W2900768265 @default.
- W3082775802 hasRelatedWork W2901189993 @default.
- W3082775802 hasRelatedWork W2937843571 @default.
- W3082775802 hasRelatedWork W2945297805 @default.
- W3082775802 hasRelatedWork W2948730003 @default.
- W3082775802 hasRelatedWork W2954930822 @default.
- W3082775802 hasRelatedWork W2964091144 @default.
- W3082775802 hasRelatedWork W2981553018 @default.
- W3082775802 hasRelatedWork W2996699350 @default.
- W3082775802 hasRelatedWork W3010433305 @default.
- W3082775802 hasRelatedWork W3017990003 @default.
- W3082775802 hasRelatedWork W3098024612 @default.
- W3082775802 hasRelatedWork W3099780516 @default.
- W3082775802 hasRelatedWork W3162137573 @default.
- W3082775802 hasRelatedWork W3199885658 @default.
- W3082775802 hasRelatedWork W4226205812 @default.
- W3082775802 isParatext "false" @default.
- W3082775802 isRetracted "false" @default.
- W3082775802 magId "3082775802" @default.
- W3082775802 workType "dissertation" @default.