Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288330953> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4288330953 abstract "Modern neural network modules which can significantly enhance the learning power usually add too much computational complexity to the original neural networks. In this paper, we pursue very efficient neural network modules which can significantly boost the learning power of deep convolutional neural networks with negligible extra computational cost. We first present both theoretically and experimentally that elementwise square operator has a potential to enhance the learning power of neural networks. Then, we design four types of lightweight modules with elementwise square operators, named as Square-Pooling, Square-Softmin, Square-Excitation, and Square-Encoding. We add our four lightweight modules to Resnet18, Resnet50, and ShuffleNetV2 for better performance in the experiment on ImageNet 2012 dataset. The experimental results show that our modules can bring significant accuracy improvements to the base convolutional neural network models. The performance of our lightweight modules is even comparable to many complicated modules such as bilinear pooling, Squeeze-and-Excitation, and Gather-Excite. Our highly efficient modules are particularly suitable for mobile models. For example, when equipped with a single Square-Pooling module, the top-1 classification accuracy of ShuffleNetV2-0.5x on ImageNet 2012 is absolutely improved by 1.45% with no additional parameters and negligible inference time overhead." @default.
- W4288330953 created "2022-07-28" @default.
- W4288330953 creator A5002319878 @default.
- W4288330953 creator A5004145168 @default.
- W4288330953 creator A5017804889 @default.
- W4288330953 creator A5030941780 @default.
- W4288330953 creator A5056101043 @default.
- W4288330953 creator A5056248574 @default.
- W4288330953 date "2019-06-12" @default.
- W4288330953 modified "2023-09-30" @default.
- W4288330953 title "DeepSquare: Boosting the Learning Power of Deep Convolutional Neural Networks with Elementwise Square Operators" @default.
- W4288330953 doi "https://doi.org/10.48550/arxiv.1906.04979" @default.
- W4288330953 hasPublicationYear "2019" @default.
- W4288330953 type Work @default.
- W4288330953 citedByCount "0" @default.
- W4288330953 crossrefType "posted-content" @default.
- W4288330953 hasAuthorship W4288330953A5002319878 @default.
- W4288330953 hasAuthorship W4288330953A5004145168 @default.
- W4288330953 hasAuthorship W4288330953A5017804889 @default.
- W4288330953 hasAuthorship W4288330953A5030941780 @default.
- W4288330953 hasAuthorship W4288330953A5056101043 @default.
- W4288330953 hasAuthorship W4288330953A5056248574 @default.
- W4288330953 hasBestOaLocation W42883309531 @default.
- W4288330953 hasConcept C108583219 @default.
- W4288330953 hasConcept C11413529 @default.
- W4288330953 hasConcept C119857082 @default.
- W4288330953 hasConcept C121332964 @default.
- W4288330953 hasConcept C135692309 @default.
- W4288330953 hasConcept C154945302 @default.
- W4288330953 hasConcept C163258240 @default.
- W4288330953 hasConcept C205203396 @default.
- W4288330953 hasConcept C2524010 @default.
- W4288330953 hasConcept C2776214188 @default.
- W4288330953 hasConcept C31972630 @default.
- W4288330953 hasConcept C33923547 @default.
- W4288330953 hasConcept C41008148 @default.
- W4288330953 hasConcept C46686674 @default.
- W4288330953 hasConcept C50644808 @default.
- W4288330953 hasConcept C62520636 @default.
- W4288330953 hasConcept C70437156 @default.
- W4288330953 hasConcept C81363708 @default.
- W4288330953 hasConceptScore W4288330953C108583219 @default.
- W4288330953 hasConceptScore W4288330953C11413529 @default.
- W4288330953 hasConceptScore W4288330953C119857082 @default.
- W4288330953 hasConceptScore W4288330953C121332964 @default.
- W4288330953 hasConceptScore W4288330953C135692309 @default.
- W4288330953 hasConceptScore W4288330953C154945302 @default.
- W4288330953 hasConceptScore W4288330953C163258240 @default.
- W4288330953 hasConceptScore W4288330953C205203396 @default.
- W4288330953 hasConceptScore W4288330953C2524010 @default.
- W4288330953 hasConceptScore W4288330953C2776214188 @default.
- W4288330953 hasConceptScore W4288330953C31972630 @default.
- W4288330953 hasConceptScore W4288330953C33923547 @default.
- W4288330953 hasConceptScore W4288330953C41008148 @default.
- W4288330953 hasConceptScore W4288330953C46686674 @default.
- W4288330953 hasConceptScore W4288330953C50644808 @default.
- W4288330953 hasConceptScore W4288330953C62520636 @default.
- W4288330953 hasConceptScore W4288330953C70437156 @default.
- W4288330953 hasConceptScore W4288330953C81363708 @default.
- W4288330953 hasLocation W42883309531 @default.
- W4288330953 hasOpenAccess W4288330953 @default.
- W4288330953 hasPrimaryLocation W42883309531 @default.
- W4288330953 hasRelatedWork W2337926734 @default.
- W4288330953 hasRelatedWork W2517027266 @default.
- W4288330953 hasRelatedWork W2914959431 @default.
- W4288330953 hasRelatedWork W2963958939 @default.
- W4288330953 hasRelatedWork W4220996320 @default.
- W4288330953 hasRelatedWork W4311257506 @default.
- W4288330953 hasRelatedWork W4319994054 @default.
- W4288330953 hasRelatedWork W4320802194 @default.
- W4288330953 hasRelatedWork W4321369474 @default.
- W4288330953 hasRelatedWork W4327499916 @default.
- W4288330953 isParatext "false" @default.
- W4288330953 isRetracted "false" @default.
- W4288330953 workType "article" @default.