Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312584711> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W4312584711 endingPage "112788" @default.
- W4312584711 startingPage "112776" @default.
- W4312584711 abstract "Due to the black-box nature of deep networks, making explanations of their decision-making is extremely challenging. A solution is using post-hoc attention mechanisms with the deep network to verify the decision basis. However, those methods have problems such as gradient noise and false confidence. In addition, existing saliency methods either have limited performance by using only the last convolution layer or suffer from large computational overhead. In this work, we propose the Collection-CAM, which generates an attention map with low computational overhead while utilizing multi-level feature maps. First, the Collection-CAM searches for the most appropriate form of the partition through bottom-up clustering and clustering validation process. Then the Collection-CAM applies different pre-processing procedures on the shallow feature map and final feature map to overcome the false positiveness when applied without distinction. By combining collection-wise masks according to their contribution to the confidence score, the Collection-CAM completes the attention map generation process. Experimental results on ImageNet1k, UC Merced, and CUB dataset and various deep network models demonstrate that the Collection-CAM not only can synthesize a saliency map with a better visual explanation but also requires significantly lower computational overhead compared to those of region-based saliency methods." @default.
- W4312584711 created "2023-01-05" @default.
- W4312584711 creator A5045403869 @default.
- W4312584711 creator A5054923848 @default.
- W4312584711 date "2022-01-01" @default.
- W4312584711 modified "2023-10-18" @default.
- W4312584711 title "Collection-CAM: A Faster Region-Based Saliency Method Using Collection-Wise Mask Over Pyramidal Features" @default.
- W4312584711 doi "https://doi.org/10.1109/access.2022.3215534" @default.
- W4312584711 hasPublicationYear "2022" @default.
- W4312584711 type Work @default.
- W4312584711 citedByCount "0" @default.
- W4312584711 crossrefType "journal-article" @default.
- W4312584711 hasAuthorship W4312584711A5045403869 @default.
- W4312584711 hasAuthorship W4312584711A5054923848 @default.
- W4312584711 hasBestOaLocation W43125847111 @default.
- W4312584711 hasConcept C105795698 @default.
- W4312584711 hasConcept C111919701 @default.
- W4312584711 hasConcept C114614502 @default.
- W4312584711 hasConcept C119857082 @default.
- W4312584711 hasConcept C124101348 @default.
- W4312584711 hasConcept C133462117 @default.
- W4312584711 hasConcept C138885662 @default.
- W4312584711 hasConcept C153180895 @default.
- W4312584711 hasConcept C154945302 @default.
- W4312584711 hasConcept C2776401178 @default.
- W4312584711 hasConcept C2779960059 @default.
- W4312584711 hasConcept C33923547 @default.
- W4312584711 hasConcept C41008148 @default.
- W4312584711 hasConcept C41895202 @default.
- W4312584711 hasConcept C42812 @default.
- W4312584711 hasConcept C73555534 @default.
- W4312584711 hasConcept C98045186 @default.
- W4312584711 hasConceptScore W4312584711C105795698 @default.
- W4312584711 hasConceptScore W4312584711C111919701 @default.
- W4312584711 hasConceptScore W4312584711C114614502 @default.
- W4312584711 hasConceptScore W4312584711C119857082 @default.
- W4312584711 hasConceptScore W4312584711C124101348 @default.
- W4312584711 hasConceptScore W4312584711C133462117 @default.
- W4312584711 hasConceptScore W4312584711C138885662 @default.
- W4312584711 hasConceptScore W4312584711C153180895 @default.
- W4312584711 hasConceptScore W4312584711C154945302 @default.
- W4312584711 hasConceptScore W4312584711C2776401178 @default.
- W4312584711 hasConceptScore W4312584711C2779960059 @default.
- W4312584711 hasConceptScore W4312584711C33923547 @default.
- W4312584711 hasConceptScore W4312584711C41008148 @default.
- W4312584711 hasConceptScore W4312584711C41895202 @default.
- W4312584711 hasConceptScore W4312584711C42812 @default.
- W4312584711 hasConceptScore W4312584711C73555534 @default.
- W4312584711 hasConceptScore W4312584711C98045186 @default.
- W4312584711 hasFunder F4320322093 @default.
- W4312584711 hasFunder F4320323103 @default.
- W4312584711 hasFunder F4320332195 @default.
- W4312584711 hasLocation W43125847111 @default.
- W4312584711 hasLocation W43125847112 @default.
- W4312584711 hasOpenAccess W4312584711 @default.
- W4312584711 hasPrimaryLocation W43125847111 @default.
- W4312584711 hasRelatedWork W2075832457 @default.
- W4312584711 hasRelatedWork W2382607599 @default.
- W4312584711 hasRelatedWork W2546942002 @default.
- W4312584711 hasRelatedWork W2614500124 @default.
- W4312584711 hasRelatedWork W2961085424 @default.
- W4312584711 hasRelatedWork W2970216048 @default.
- W4312584711 hasRelatedWork W3010198599 @default.
- W4312584711 hasRelatedWork W4286629047 @default.
- W4312584711 hasRelatedWork W4306674287 @default.
- W4312584711 hasRelatedWork W4224009465 @default.
- W4312584711 hasVolume "10" @default.
- W4312584711 isParatext "false" @default.
- W4312584711 isRetracted "false" @default.
- W4312584711 workType "article" @default.