Matches in SemOpenAlex for { <https://semopenalex.org/work/W3208552997> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W3208552997 abstract "Many attention models have been introduced to boost the representational power of convolutional neural networks (CNNs). Most of them are self-attention models which generate an attention mask based on current features, like spatial attention and channel attention model. However, these attention models may not achieve good results when the current features are the low-level features of CNNs. In this work, we propose a new lightweight attention unit, feature difference (FD) model, which utilizes the difference between two feature maps to generate the attention mask. The FD module can be integrated into most of the state-of-the-art CNNs like ResNets and VGG just by adding some shortcut connections, which does not introduce any additional parameters and layers. Extensive experiments show that the FD model can help improve the performance of the baseline on four benchmarks, including CIFAR10, CIFAR100, ImageNet-1K, and VOC PASCAL. Note that ResNet44 (6.10% error) with FD model achieves better results than ResNet56 (6.24% error), while the former has fewer parameters than the latter one by 29%." @default.
- W3208552997 created "2021-11-08" @default.
- W3208552997 creator A5030671553 @default.
- W3208552997 creator A5070035384 @default.
- W3208552997 creator A5073779363 @default.
- W3208552997 creator A5079170636 @default.
- W3208552997 date "2021-01-01" @default.
- W3208552997 modified "2023-10-17" @default.
- W3208552997 title "Convolution Tells Where to Look" @default.
- W3208552997 cites W1849277567 @default.
- W3208552997 cites W1901129140 @default.
- W3208552997 cites W1983366569 @default.
- W3208552997 cites W1991434325 @default.
- W3208552997 cites W2013068849 @default.
- W3208552997 cites W2045758998 @default.
- W3208552997 cites W2108598243 @default.
- W3208552997 cites W2121049815 @default.
- W3208552997 cites W2142796031 @default.
- W3208552997 cites W2194775991 @default.
- W3208552997 cites W2461475918 @default.
- W3208552997 cites W2549139847 @default.
- W3208552997 cites W2752782242 @default.
- W3208552997 cites W2884585870 @default.
- W3208552997 cites W2922509574 @default.
- W3208552997 cites W2962858109 @default.
- W3208552997 cites W2963163009 @default.
- W3208552997 cites W2963495494 @default.
- W3208552997 cites W2963918968 @default.
- W3208552997 doi "https://doi.org/10.1007/978-3-030-88013-2_2" @default.
- W3208552997 hasPublicationYear "2021" @default.
- W3208552997 type Work @default.
- W3208552997 sameAs 3208552997 @default.
- W3208552997 citedByCount "0" @default.
- W3208552997 crossrefType "book-chapter" @default.
- W3208552997 hasAuthorship W3208552997A5030671553 @default.
- W3208552997 hasAuthorship W3208552997A5070035384 @default.
- W3208552997 hasAuthorship W3208552997A5073779363 @default.
- W3208552997 hasAuthorship W3208552997A5079170636 @default.
- W3208552997 hasConcept C11413529 @default.
- W3208552997 hasConcept C127162648 @default.
- W3208552997 hasConcept C138885662 @default.
- W3208552997 hasConcept C153180895 @default.
- W3208552997 hasConcept C154945302 @default.
- W3208552997 hasConcept C199360897 @default.
- W3208552997 hasConcept C2776401178 @default.
- W3208552997 hasConcept C41008148 @default.
- W3208552997 hasConcept C41895202 @default.
- W3208552997 hasConcept C45347329 @default.
- W3208552997 hasConcept C50644808 @default.
- W3208552997 hasConcept C75608658 @default.
- W3208552997 hasConcept C76155785 @default.
- W3208552997 hasConcept C81363708 @default.
- W3208552997 hasConceptScore W3208552997C11413529 @default.
- W3208552997 hasConceptScore W3208552997C127162648 @default.
- W3208552997 hasConceptScore W3208552997C138885662 @default.
- W3208552997 hasConceptScore W3208552997C153180895 @default.
- W3208552997 hasConceptScore W3208552997C154945302 @default.
- W3208552997 hasConceptScore W3208552997C199360897 @default.
- W3208552997 hasConceptScore W3208552997C2776401178 @default.
- W3208552997 hasConceptScore W3208552997C41008148 @default.
- W3208552997 hasConceptScore W3208552997C41895202 @default.
- W3208552997 hasConceptScore W3208552997C45347329 @default.
- W3208552997 hasConceptScore W3208552997C50644808 @default.
- W3208552997 hasConceptScore W3208552997C75608658 @default.
- W3208552997 hasConceptScore W3208552997C76155785 @default.
- W3208552997 hasConceptScore W3208552997C81363708 @default.
- W3208552997 hasLocation W32085529971 @default.
- W3208552997 hasOpenAccess W3208552997 @default.
- W3208552997 hasPrimaryLocation W32085529971 @default.
- W3208552997 hasRelatedWork W10116868 @default.
- W3208552997 hasRelatedWork W12775346 @default.
- W3208552997 hasRelatedWork W12874744 @default.
- W3208552997 hasRelatedWork W13715941 @default.
- W3208552997 hasRelatedWork W14569654 @default.
- W3208552997 hasRelatedWork W1496815 @default.
- W3208552997 hasRelatedWork W3092890 @default.
- W3208552997 hasRelatedWork W3143391 @default.
- W3208552997 hasRelatedWork W4136762 @default.
- W3208552997 hasRelatedWork W9190101 @default.
- W3208552997 isParatext "false" @default.
- W3208552997 isRetracted "false" @default.
- W3208552997 magId "3208552997" @default.
- W3208552997 workType "book-chapter" @default.