Deep neural network to extract high-level features and labels in multi-label classification problems

Bello, Marilyn; Nápoles, Gonzalo; Sánchez, Ricardo; Bello, Rafael; Vanhoof, Koen

doi:10.1016/j.neucom.2020.06.117

Cited by 34 publications

(11 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 2 displays the results of our measure in the model proposed by [1]. These tables report the number of high-level features, the reduction percentage those high-level features represent (%Red-Features), the number of high-level labels, the reduction percentage in the number of labels (%Red-Labels), the accuracy obtained when using only the high-level features and labels, and the accuracy loss with respect the model using all features and labels (i.e.…”

Section: Resultsmentioning

confidence: 99%

“…Recently, in [1] the authors introduced a new bidirectional network architecture that is composed of stacked association-based pooling layers to extract high-level features and labels in MLC problems. This approach, unlike the classic use of pooling, does not pool pixels but problem features or labels.…”

Section: Bidirectional Deep Neural Networkmentioning

confidence: 99%

“…Also, the average maximal correlation of Pearson according to both features and labels is reported. The simulations aim at comparing our approach with the correlation-based method proposed in [1]. In order to make fair comparisons, we will use the same network architecture proposed by the authors.…”

Section: Simulationsmentioning

confidence: 99%

“…recognizing faces, coloring black and white images or classifying objects in photographs). In [1] the authors introduced the association-based pooling that exploits the correlation among neurons instead of exploiting the topological information as typically occurs when using standard pooling operators. Despite of the relatively good results reported by this model, the function used to quantify the association between problem variables does not seem to be suitable for datasets having poor correlation among their features or labels.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Feature and Label Association Based on Granulation Entropy for Deep Neural Networks

et al. 2020

Self Cite

View full text Add to dashboard Cite

Pooling layers help reduce redundancy and the number of parameters before building a multilayered neural network that performs the remaining processing operations. Usually, pooling operators in deep learning models use an explicit topological organization, which is not always possible to obtain on multi-label data. In a previous paper, we proposed a pooling architecture based on association to deal with this issue. The association was defined by means of Pearson's correlation. However, features must exhibit a certain degree of correlation with each other, which might not hold in all situations. In this paper, we propose a new method that replaces the correlation measure with another one that computes the entropy in the information granules that are generated from two features or labels. Numerical simulations have shown that our proposal is superior in those datasets with low correlation. This means that it induces a significant reduction in the number of parameters of neural networks, without affecting their accuracy.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Bidirectional Deep Neural Networkmentioning

confidence: 99%

Section: Simulationsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Feature and Label Association Based on Granulation Entropy for Deep Neural Networks

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…The current progress of Deep Learning (DL) depends on skills including initial weight selection, local receptive fields, weight sharing, etc., when using deeper networks (such as> 100), there still has to face the traditional difficulties of disappearing gradients during backpropagation: degradation problem [33]. The more layers, the higher the training error-rate and the test error rate.…”

Section: Deep Residual Networkmentioning

confidence: 99%

An Improved Residual-Network Model-based Conditional Generative Adversarial Network Plantar Pressure Image Classification: A Comparison of Normal, Planus, and Talipes Equinovarus Feet

Han

Wang

et al. 2021

Preprint

View full text Add to dashboard Cite

The number of layers of deep learning (DL) increases, and following the performance of computing nodes improvement, the output accuracy of deep neural networks (DNN) faces a bottleneck problem. The resident network (RN) based DNN model was applied to address these issues recently. This paper improved the RN and developed a rectified linear unit (ReLU) based conditional generative adversarial nets (cGAN) to classify plantar pressure images. A foot scan system collected the plantar pressure images, in which normal (N), planus (PL), and talipes equinovarus feet (TE) data-sets were acquired subsequently. The 9-foot types named N, PL, TE, N-PL, N-TE, PL-N, PL-TE, TE-N, and TE-PL were classified using the proposed DNN models, named resident network-based conditional generative adversarial nets (RNcGAN). It improved the RN structure firstly and the cGAN system hereafter. In the classification of plantar pressure images, the pixel-level state matrix can be direct as an input, which is different from the previous image classification task with image reduction and feature extraction. cGAN can directly output the pixels of the image without any simplification. Finally, the model achieved better results in the evaluation indicators of accuracy (AC), sensitivity (SE), and F1-measurement (F1) by comparing to artificial neural networks (ANN), k-nearest neighbor (kNN), Fast Region-based Convolution Neural Network (Fast R-CNN), visual geometry group (VGG16), scaled-conjugate-gradient convolution neural networks (SCG-CNN), GoogleNet, AlexNet, ResNet-50-177, and Inception-v3. The final prediction of class accuracy is 95.17%. Foot type classification is vital for producing comfortable shoes in the industry.

show abstract

Histopathological Image Classification Using Ensemble Transfer Learning

Devassy

Antony²

2021

Machine Learning and Big Data Analytics (Proceedings of International Conference on Machine Learning and Big Data Analytics (IC

View full text Add to dashboard Cite

Deep neural network to extract high-level features and labels in multi-label classification problems

Cited by 34 publications

References 40 publications

Feature and Label Association Based on Granulation Entropy for Deep Neural Networks

Feature and Label Association Based on Granulation Entropy for Deep Neural Networks

An Improved Residual-Network Model-based Conditional Generative Adversarial Network Plantar Pressure Image Classification: A Comparison of Normal, Planus, and Talipes Equinovarus Feet

Histopathological Image Classification Using Ensemble Transfer Learning

Contact Info

Product

Resources

About