Matches in SemOpenAlex for { <https://semopenalex.org/work/W2790958480> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W2790958480 abstract "Convolutional neural networks have many hyperparameters such as the filter size, number of filters, and pooling size, which require manual tuning. Though deep stacked structures are able to create multi-scale and hierarchical representations, manually fixed filter sizes limit the scale of representations that can be learned in a single convolutional layer. This paper introduces a new adaptive filter model that allows variable scale and orientation. The scale and orientation parameters of filters can be learned using back propagation. Therefore, in a single convolution layer, we can create filters of different scale and orientation that can adapt to small or large features and objects. The proposed model uses a relatively large base size (grid) for filters. In the grid, a differentiable function acts as an envelope for the filters. The envelope function guides effective filter scale and shape/orientation by masking the filter weights before the convolution. Therefore, only the weights in the envelope are updated during training. In this work, we employed a multivariate (2D) Gaussian as the envelope function and showed that it can grow, shrink, or rotate by updating its covariance matrix during back propagation training . We tested the new filter model on MNIST, MNIST-cluttered, and CIFAR-10 and compared the results with the networks that used conventional convolution layers. The results demonstrate that the new model can effectively learn and produce filters of different scales and orientations in a single layer. Moreover, the experiments show that the adaptive convolution layers perform equally; or better, especially when data includes objects of varying scale and noisy backgrounds." @default.
- W2790958480 created "2018-03-29" @default.
- W2790958480 creator A5019546479 @default.
- W2790958480 creator A5045110953 @default.
- W2790958480 date "2018-02-13" @default.
- W2790958480 modified "2023-09-27" @default.
- W2790958480 title "Learning Filter Scale and Orientation In CNNs." @default.
- W2790958480 cites W2004217976 @default.
- W2790958480 cites W2112328181 @default.
- W2790958480 cites W2112796928 @default.
- W2790958480 cites W2124386111 @default.
- W2790958480 cites W2144982973 @default.
- W2790958480 cites W2161969291 @default.
- W2790958480 cites W3038058348 @default.
- W2790958480 cites W3118608800 @default.
- W2790958480 hasPublicationYear "2018" @default.
- W2790958480 type Work @default.
- W2790958480 sameAs 2790958480 @default.
- W2790958480 citedByCount "1" @default.
- W2790958480 countsByYear W27909584802020 @default.
- W2790958480 crossrefType "posted-content" @default.
- W2790958480 hasAuthorship W2790958480A5019546479 @default.
- W2790958480 hasAuthorship W2790958480A5045110953 @default.
- W2790958480 hasConcept C106131492 @default.
- W2790958480 hasConcept C108583219 @default.
- W2790958480 hasConcept C11413529 @default.
- W2790958480 hasConcept C115961682 @default.
- W2790958480 hasConcept C121332964 @default.
- W2790958480 hasConcept C153180895 @default.
- W2790958480 hasConcept C154945302 @default.
- W2790958480 hasConcept C16345878 @default.
- W2790958480 hasConcept C190502265 @default.
- W2790958480 hasConcept C2524010 @default.
- W2790958480 hasConcept C2778755073 @default.
- W2790958480 hasConcept C31972630 @default.
- W2790958480 hasConcept C33923547 @default.
- W2790958480 hasConcept C41008148 @default.
- W2790958480 hasConcept C45347329 @default.
- W2790958480 hasConcept C50644808 @default.
- W2790958480 hasConcept C554190296 @default.
- W2790958480 hasConcept C62520636 @default.
- W2790958480 hasConcept C65155139 @default.
- W2790958480 hasConcept C65892221 @default.
- W2790958480 hasConcept C76155785 @default.
- W2790958480 hasConcept C81363708 @default.
- W2790958480 hasConceptScore W2790958480C106131492 @default.
- W2790958480 hasConceptScore W2790958480C108583219 @default.
- W2790958480 hasConceptScore W2790958480C11413529 @default.
- W2790958480 hasConceptScore W2790958480C115961682 @default.
- W2790958480 hasConceptScore W2790958480C121332964 @default.
- W2790958480 hasConceptScore W2790958480C153180895 @default.
- W2790958480 hasConceptScore W2790958480C154945302 @default.
- W2790958480 hasConceptScore W2790958480C16345878 @default.
- W2790958480 hasConceptScore W2790958480C190502265 @default.
- W2790958480 hasConceptScore W2790958480C2524010 @default.
- W2790958480 hasConceptScore W2790958480C2778755073 @default.
- W2790958480 hasConceptScore W2790958480C31972630 @default.
- W2790958480 hasConceptScore W2790958480C33923547 @default.
- W2790958480 hasConceptScore W2790958480C41008148 @default.
- W2790958480 hasConceptScore W2790958480C45347329 @default.
- W2790958480 hasConceptScore W2790958480C50644808 @default.
- W2790958480 hasConceptScore W2790958480C554190296 @default.
- W2790958480 hasConceptScore W2790958480C62520636 @default.
- W2790958480 hasConceptScore W2790958480C65155139 @default.
- W2790958480 hasConceptScore W2790958480C65892221 @default.
- W2790958480 hasConceptScore W2790958480C76155785 @default.
- W2790958480 hasConceptScore W2790958480C81363708 @default.
- W2790958480 hasLocation W27909584801 @default.
- W2790958480 hasOpenAccess W2790958480 @default.
- W2790958480 hasPrimaryLocation W27909584801 @default.
- W2790958480 hasRelatedWork W146422257 @default.
- W2790958480 hasRelatedWork W1983284560 @default.
- W2790958480 hasRelatedWork W2121504967 @default.
- W2790958480 hasRelatedWork W2294045597 @default.
- W2790958480 hasRelatedWork W2552292250 @default.
- W2790958480 hasRelatedWork W2892916125 @default.
- W2790958480 hasRelatedWork W2912083667 @default.
- W2790958480 hasRelatedWork W2913531435 @default.
- W2790958480 hasRelatedWork W2921604020 @default.
- W2790958480 hasRelatedWork W2924489837 @default.
- W2790958480 hasRelatedWork W2955983623 @default.
- W2790958480 hasRelatedWork W2985516908 @default.
- W2790958480 hasRelatedWork W2998645105 @default.
- W2790958480 hasRelatedWork W2998855979 @default.
- W2790958480 hasRelatedWork W3100907676 @default.
- W2790958480 hasRelatedWork W3130114846 @default.
- W2790958480 hasRelatedWork W3136623851 @default.
- W2790958480 hasRelatedWork W3168696965 @default.
- W2790958480 hasRelatedWork W3204266120 @default.
- W2790958480 hasRelatedWork W3168339986 @default.
- W2790958480 isParatext "false" @default.
- W2790958480 isRetracted "false" @default.
- W2790958480 magId "2790958480" @default.
- W2790958480 workType "article" @default.