Matches in SemOpenAlex for { <https://semopenalex.org/work/W2937557681> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W2937557681 endingPage "94" @default.
- W2937557681 startingPage "79" @default.
- W2937557681 abstract "Convolutional Neural Network has become very common in the field of computer vision in recent years. But it comes with a severe restriction regarding the size of the input image. Most convolutional neural networks are designed in a way so that they can only accept images of a fixed size. This creates several challenges during data acquisition and model deployment. The common practice to overcome this limitation is to reshape the input images so that they can be fed into the networks. Many standard pre-trained networks and datasets come with a provision of working with square images. In this work we analyze 25 different reshaping methods across 6 datasets corresponding to different domains trained on three famous architectures namely Inception-V3, which is an extension of GoogLeNet, the Residual Networks (Resent-18) and the 121-Layer deep DenseNet. While some of the reshaping methods like “interpolation” and “cropping” have been commonly used with convolutional neural networks, some uncommon techniques like “containing”, “tiling” and “mirroring” have also been demonstrated. In total, 450 neural networks were trained from scratch to provide various analyses regarding the convergence of the validation loss and the accuracy obtained on the test data. Statistical measures have been provided to demonstrate the dependence between parameter choices and datasets. Several key observations were noted such as the benefits of using randomized processes, poor performance of the commonly used “cropping” techniques and so on. The paper intends to provide empirical evidence to guide the reader to choose a proper technique of reshaping inputs for their convolutional neural networks. The official code is available in https://github.com/DVLP-CMATERJU/Reshaping-Inputs-for-CNN." @default.
- W2937557681 created "2019-04-25" @default.
- W2937557681 creator A5000210772 @default.
- W2937557681 creator A5037158329 @default.
- W2937557681 creator A5070947372 @default.
- W2937557681 date "2019-09-01" @default.
- W2937557681 modified "2023-10-02" @default.
- W2937557681 title "Reshaping inputs for convolutional neural network: Some common and uncommon methods" @default.
- W2937557681 cites W1521436688 @default.
- W2937557681 cites W1989725585 @default.
- W2937557681 cites W1996303439 @default.
- W2937557681 cites W2031489346 @default.
- W2937557681 cites W2076063813 @default.
- W2937557681 cites W2088869937 @default.
- W2937557681 cites W2108069432 @default.
- W2937557681 cites W2110764733 @default.
- W2937557681 cites W2112796928 @default.
- W2937557681 cites W2117539524 @default.
- W2937557681 cites W2161663128 @default.
- W2937557681 cites W2165698076 @default.
- W2937557681 cites W2185175083 @default.
- W2937557681 cites W2248723555 @default.
- W2937557681 cites W2253590344 @default.
- W2937557681 cites W2592852541 @default.
- W2937557681 cites W2620281313 @default.
- W2937557681 doi "https://doi.org/10.1016/j.patcog.2019.04.009" @default.
- W2937557681 hasPublicationYear "2019" @default.
- W2937557681 type Work @default.
- W2937557681 sameAs 2937557681 @default.
- W2937557681 citedByCount "40" @default.
- W2937557681 countsByYear W29375576812019 @default.
- W2937557681 countsByYear W29375576812020 @default.
- W2937557681 countsByYear W29375576812021 @default.
- W2937557681 countsByYear W29375576812022 @default.
- W2937557681 countsByYear W29375576812023 @default.
- W2937557681 crossrefType "journal-article" @default.
- W2937557681 hasAuthorship W2937557681A5000210772 @default.
- W2937557681 hasAuthorship W2937557681A5037158329 @default.
- W2937557681 hasAuthorship W2937557681A5070947372 @default.
- W2937557681 hasConcept C11413529 @default.
- W2937557681 hasConcept C115961682 @default.
- W2937557681 hasConcept C119857082 @default.
- W2937557681 hasConcept C124101348 @default.
- W2937557681 hasConcept C137800194 @default.
- W2937557681 hasConcept C153180895 @default.
- W2937557681 hasConcept C154945302 @default.
- W2937557681 hasConcept C155512373 @default.
- W2937557681 hasConcept C162324750 @default.
- W2937557681 hasConcept C202444582 @default.
- W2937557681 hasConcept C26517878 @default.
- W2937557681 hasConcept C2777303404 @default.
- W2937557681 hasConcept C33923547 @default.
- W2937557681 hasConcept C38652104 @default.
- W2937557681 hasConcept C41008148 @default.
- W2937557681 hasConcept C50522688 @default.
- W2937557681 hasConcept C50644808 @default.
- W2937557681 hasConcept C81363708 @default.
- W2937557681 hasConcept C9652623 @default.
- W2937557681 hasConceptScore W2937557681C11413529 @default.
- W2937557681 hasConceptScore W2937557681C115961682 @default.
- W2937557681 hasConceptScore W2937557681C119857082 @default.
- W2937557681 hasConceptScore W2937557681C124101348 @default.
- W2937557681 hasConceptScore W2937557681C137800194 @default.
- W2937557681 hasConceptScore W2937557681C153180895 @default.
- W2937557681 hasConceptScore W2937557681C154945302 @default.
- W2937557681 hasConceptScore W2937557681C155512373 @default.
- W2937557681 hasConceptScore W2937557681C162324750 @default.
- W2937557681 hasConceptScore W2937557681C202444582 @default.
- W2937557681 hasConceptScore W2937557681C26517878 @default.
- W2937557681 hasConceptScore W2937557681C2777303404 @default.
- W2937557681 hasConceptScore W2937557681C33923547 @default.
- W2937557681 hasConceptScore W2937557681C38652104 @default.
- W2937557681 hasConceptScore W2937557681C41008148 @default.
- W2937557681 hasConceptScore W2937557681C50522688 @default.
- W2937557681 hasConceptScore W2937557681C50644808 @default.
- W2937557681 hasConceptScore W2937557681C81363708 @default.
- W2937557681 hasConceptScore W2937557681C9652623 @default.
- W2937557681 hasFunder F4320334771 @default.
- W2937557681 hasLocation W29375576811 @default.
- W2937557681 hasOpenAccess W2937557681 @default.
- W2937557681 hasPrimaryLocation W29375576811 @default.
- W2937557681 hasRelatedWork W2102025433 @default.
- W2937557681 hasRelatedWork W2386606084 @default.
- W2937557681 hasRelatedWork W2767651786 @default.
- W2937557681 hasRelatedWork W2912288872 @default.
- W2937557681 hasRelatedWork W2961085424 @default.
- W2937557681 hasRelatedWork W3021430260 @default.
- W2937557681 hasRelatedWork W3027997911 @default.
- W2937557681 hasRelatedWork W3206466808 @default.
- W2937557681 hasRelatedWork W4287776258 @default.
- W2937557681 hasRelatedWork W564581980 @default.
- W2937557681 hasVolume "93" @default.
- W2937557681 isParatext "false" @default.
- W2937557681 isRetracted "false" @default.
- W2937557681 magId "2937557681" @default.
- W2937557681 workType "article" @default.