Matches in SemOpenAlex for { <https://semopenalex.org/work/W4243330187> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4243330187 abstract "Feature selection and transformation are the important techniques in machine learning field. A good feature selection or transformation will greatly improve the performance of classification method. In this work, we proposed a simple but efficient image classification method which is based on two-stage processing strategy. In the first stage, the one-dimensional features are obtained from image by transfer learning with the pre-trained Deep Convolutional Neural Networks (DCNN). These one-dimensional DCNN features still have the shortcomings of information redundancy and weak distinguishing ability. Therefore, it is necessary to use feature transformation to further obtain more discriminative features. We propose a feature learning and selective transformation network based on Long Short-Term Memory (LSTM) combing ReLU and Dropout layers (called LSTM-RDN) to further process one-dimensional DCNN features. The verification experiments were conducted on three public object image datasets (Cifar10, Cifar100 and Fashion-MNIST), three fine-grained image datasets (CUB200-2011, Stanford-Cars, FGVC-Aircraft) and a COVID-19 dataset, and several backbone network models were used, including AlexNet, VGG16, ResNet18, ResNet101, InceptionV2 and EfficientNet-b0. Experimental results have shown that the recognition performance of the proposed method can significantly exceed the performance of existing state-of-the-art methods. The level of machine vision classification has reached the bottleneck, it is difficult to solve this problem by using a large-scale network model which has huge parameters that need to be optimized. We present an effective approach for breaking through the bottleneck of visual classification task by feature extraction with backbone DCNN and feature selective transformation with LSTM-RDN, separately. The code and pre-trained models are available from: https://github.com/lillllllll/LSTM-RDN" @default.
- W4243330187 created "2022-05-12" @default.
- W4243330187 creator A5005321044 @default.
- W4243330187 creator A5007621167 @default.
- W4243330187 creator A5022630086 @default.
- W4243330187 creator A5025945671 @default.
- W4243330187 date "2021-06-02" @default.
- W4243330187 modified "2023-09-30" @default.
- W4243330187 title "One-dimensional DCNN Feature Selective Transformation with LSTM-RDN for Image Classification" @default.
- W4243330187 doi "https://doi.org/10.36227/techrxiv.14642814" @default.
- W4243330187 hasPublicationYear "2021" @default.
- W4243330187 type Work @default.
- W4243330187 citedByCount "0" @default.
- W4243330187 crossrefType "posted-content" @default.
- W4243330187 hasAuthorship W4243330187A5005321044 @default.
- W4243330187 hasAuthorship W4243330187A5007621167 @default.
- W4243330187 hasAuthorship W4243330187A5022630086 @default.
- W4243330187 hasAuthorship W4243330187A5025945671 @default.
- W4243330187 hasBestOaLocation W42433301871 @default.
- W4243330187 hasConcept C104317684 @default.
- W4243330187 hasConcept C108583219 @default.
- W4243330187 hasConcept C115961682 @default.
- W4243330187 hasConcept C119857082 @default.
- W4243330187 hasConcept C138885662 @default.
- W4243330187 hasConcept C148483581 @default.
- W4243330187 hasConcept C149635348 @default.
- W4243330187 hasConcept C150899416 @default.
- W4243330187 hasConcept C153180895 @default.
- W4243330187 hasConcept C154945302 @default.
- W4243330187 hasConcept C185592680 @default.
- W4243330187 hasConcept C190502265 @default.
- W4243330187 hasConcept C204241405 @default.
- W4243330187 hasConcept C2776401178 @default.
- W4243330187 hasConcept C2780513914 @default.
- W4243330187 hasConcept C41008148 @default.
- W4243330187 hasConcept C41895202 @default.
- W4243330187 hasConcept C52622490 @default.
- W4243330187 hasConcept C55493867 @default.
- W4243330187 hasConcept C75294576 @default.
- W4243330187 hasConcept C81363708 @default.
- W4243330187 hasConcept C97931131 @default.
- W4243330187 hasConceptScore W4243330187C104317684 @default.
- W4243330187 hasConceptScore W4243330187C108583219 @default.
- W4243330187 hasConceptScore W4243330187C115961682 @default.
- W4243330187 hasConceptScore W4243330187C119857082 @default.
- W4243330187 hasConceptScore W4243330187C138885662 @default.
- W4243330187 hasConceptScore W4243330187C148483581 @default.
- W4243330187 hasConceptScore W4243330187C149635348 @default.
- W4243330187 hasConceptScore W4243330187C150899416 @default.
- W4243330187 hasConceptScore W4243330187C153180895 @default.
- W4243330187 hasConceptScore W4243330187C154945302 @default.
- W4243330187 hasConceptScore W4243330187C185592680 @default.
- W4243330187 hasConceptScore W4243330187C190502265 @default.
- W4243330187 hasConceptScore W4243330187C204241405 @default.
- W4243330187 hasConceptScore W4243330187C2776401178 @default.
- W4243330187 hasConceptScore W4243330187C2780513914 @default.
- W4243330187 hasConceptScore W4243330187C41008148 @default.
- W4243330187 hasConceptScore W4243330187C41895202 @default.
- W4243330187 hasConceptScore W4243330187C52622490 @default.
- W4243330187 hasConceptScore W4243330187C55493867 @default.
- W4243330187 hasConceptScore W4243330187C75294576 @default.
- W4243330187 hasConceptScore W4243330187C81363708 @default.
- W4243330187 hasConceptScore W4243330187C97931131 @default.
- W4243330187 hasLocation W42433301871 @default.
- W4243330187 hasOpenAccess W4243330187 @default.
- W4243330187 hasPrimaryLocation W42433301871 @default.
- W4243330187 hasRelatedWork W2531896461 @default.
- W4243330187 hasRelatedWork W2732542196 @default.
- W4243330187 hasRelatedWork W2800691917 @default.
- W4243330187 hasRelatedWork W3012393889 @default.
- W4243330187 hasRelatedWork W3013138473 @default.
- W4243330187 hasRelatedWork W3018421652 @default.
- W4243330187 hasRelatedWork W3021430260 @default.
- W4243330187 hasRelatedWork W3156786002 @default.
- W4243330187 hasRelatedWork W3189091156 @default.
- W4243330187 hasRelatedWork W3195938642 @default.
- W4243330187 isParatext "false" @default.
- W4243330187 isRetracted "false" @default.
- W4243330187 workType "article" @default.