Matches in SemOpenAlex for { <https://semopenalex.org/work/W3139508830> ?p ?o ?g. }
- W3139508830 abstract "In convolutional neural network-based character recognition, pooling layers play an important role in dimensionality reduction and deformation compensation. However, their kernel shapes and pooling operations are empirically predetermined; typically, a fixed-size square kernel shape and max pooling operation are used. In this paper, we propose a meta-learning framework for pooling layers. As part of our framework, a parameterized pooling layer is proposed in which the kernel shape and pooling operation are trainable using two parameters, thereby allowing flexible pooling of the input data. We also propose a meta-learning algorithm for the parameterized pooling layer, which allows us to acquire a suitable pooling layer across multiple tasks. In the experiment, we applied the proposed meta-learning framework to character recognition tasks. The results demonstrate that a pooling layer that is suitable across character recognition tasks was obtained via meta-learning, and the obtained pooling layer improved the performance of the model in both few-shot character recognition and noisy image recognition tasks." @default.
- W3139508830 created "2021-03-29" @default.
- W3139508830 creator A5018884738 @default.
- W3139508830 creator A5036311871 @default.
- W3139508830 creator A5051387162 @default.
- W3139508830 creator A5086739419 @default.
- W3139508830 date "2021-03-17" @default.
- W3139508830 modified "2023-09-25" @default.
- W3139508830 title "Meta-learning of Pooling Layers for Character Recognition" @default.
- W3139508830 cites W1836465849 @default.
- W3139508830 cites W1840106123 @default.
- W3139508830 cites W1985222382 @default.
- W3139508830 cites W2002648693 @default.
- W3139508830 cites W2104657103 @default.
- W3139508830 cites W2133319764 @default.
- W3139508830 cites W2159386181 @default.
- W3139508830 cites W2472819217 @default.
- W3139508830 cites W2560023338 @default.
- W3139508830 cites W2604763608 @default.
- W3139508830 cites W2740620254 @default.
- W3139508830 cites W2896049206 @default.
- W3139508830 cites W2911925209 @default.
- W3139508830 cites W2948974578 @default.
- W3139508830 cites W2961719374 @default.
- W3139508830 cites W2962761264 @default.
- W3139508830 cites W2962820688 @default.
- W3139508830 cites W2963066927 @default.
- W3139508830 cites W2963166708 @default.
- W3139508830 cites W2963341924 @default.
- W3139508830 cites W2964012402 @default.
- W3139508830 cites W2964105864 @default.
- W3139508830 cites W2964112702 @default.
- W3139508830 cites W2964121744 @default.
- W3139508830 cites W2964231884 @default.
- W3139508830 cites W2964342346 @default.
- W3139508830 cites W2970144620 @default.
- W3139508830 cites W2987852271 @default.
- W3139508830 cites W2995009671 @default.
- W3139508830 cites W2997405397 @default.
- W3139508830 cites W3022178898 @default.
- W3139508830 cites W3034251792 @default.
- W3139508830 cites W3034354010 @default.
- W3139508830 cites W3034502973 @default.
- W3139508830 cites W3122369936 @default.
- W3139508830 doi "https://doi.org/10.48550/arxiv.2103.09528" @default.
- W3139508830 hasPublicationYear "2021" @default.
- W3139508830 type Work @default.
- W3139508830 sameAs 3139508830 @default.
- W3139508830 citedByCount "0" @default.
- W3139508830 crossrefType "posted-content" @default.
- W3139508830 hasAuthorship W3139508830A5018884738 @default.
- W3139508830 hasAuthorship W3139508830A5036311871 @default.
- W3139508830 hasAuthorship W3139508830A5051387162 @default.
- W3139508830 hasAuthorship W3139508830A5086739419 @default.
- W3139508830 hasBestOaLocation W31395088301 @default.
- W3139508830 hasConcept C111030470 @default.
- W3139508830 hasConcept C11413529 @default.
- W3139508830 hasConcept C114614502 @default.
- W3139508830 hasConcept C119857082 @default.
- W3139508830 hasConcept C153180895 @default.
- W3139508830 hasConcept C154945302 @default.
- W3139508830 hasConcept C165464430 @default.
- W3139508830 hasConcept C178790620 @default.
- W3139508830 hasConcept C185592680 @default.
- W3139508830 hasConcept C2524010 @default.
- W3139508830 hasConcept C2779227376 @default.
- W3139508830 hasConcept C2780861071 @default.
- W3139508830 hasConcept C33923547 @default.
- W3139508830 hasConcept C41008148 @default.
- W3139508830 hasConcept C70437156 @default.
- W3139508830 hasConcept C70518039 @default.
- W3139508830 hasConcept C74193536 @default.
- W3139508830 hasConcept C81363708 @default.
- W3139508830 hasConceptScore W3139508830C111030470 @default.
- W3139508830 hasConceptScore W3139508830C11413529 @default.
- W3139508830 hasConceptScore W3139508830C114614502 @default.
- W3139508830 hasConceptScore W3139508830C119857082 @default.
- W3139508830 hasConceptScore W3139508830C153180895 @default.
- W3139508830 hasConceptScore W3139508830C154945302 @default.
- W3139508830 hasConceptScore W3139508830C165464430 @default.
- W3139508830 hasConceptScore W3139508830C178790620 @default.
- W3139508830 hasConceptScore W3139508830C185592680 @default.
- W3139508830 hasConceptScore W3139508830C2524010 @default.
- W3139508830 hasConceptScore W3139508830C2779227376 @default.
- W3139508830 hasConceptScore W3139508830C2780861071 @default.
- W3139508830 hasConceptScore W3139508830C33923547 @default.
- W3139508830 hasConceptScore W3139508830C41008148 @default.
- W3139508830 hasConceptScore W3139508830C70437156 @default.
- W3139508830 hasConceptScore W3139508830C70518039 @default.
- W3139508830 hasConceptScore W3139508830C74193536 @default.
- W3139508830 hasConceptScore W3139508830C81363708 @default.
- W3139508830 hasLocation W31395088301 @default.
- W3139508830 hasOpenAccess W3139508830 @default.
- W3139508830 hasPrimaryLocation W31395088301 @default.
- W3139508830 hasRelatedWork W1436594442 @default.
- W3139508830 hasRelatedWork W2095834362 @default.
- W3139508830 hasRelatedWork W2375904069 @default.
- W3139508830 hasRelatedWork W2758063741 @default.
- W3139508830 hasRelatedWork W2940732649 @default.
- W3139508830 hasRelatedWork W2955667634 @default.