Fine-Tuning of Pre-Trained Deep Learning Models with Extreme Learning Machine

Alshalali, Tagrid; Josyula, Darsana P.

doi:10.1109/csci46756.2018.00096

Cited by 25 publications

(18 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We reported the use of VGG-16 [31,57,66,68,69,115] and VGG-19 [100] architectures for extracting features and fine-tuning with ELM; all of the previously mentioned studies used pre-trained weights from the ILSVRC dataset. The work [83] presented an approach to predict and classify data using a multimodal approach, where video data (frame sequencing) and audio are considered.…”

Section: Pre-trained Cnn In Other Application Domain For Feature Extraction and Elm For Fast Learningmentioning

confidence: 99%

Convolutional Extreme Learning Machines: A Systematic Review

et al. 2021

View full text Add to dashboard Cite

Much work has recently identified the need to combine deep learning with extreme learning in order to strike a performance balance with accuracy, especially in the domain of multimedia applications. When considering this new paradigm—namely, the convolutional extreme learning machine (CELM)—we present a systematic review that investigates alternative deep learning architectures that use the extreme learning machine (ELM) for faster training to solve problems that are based on image analysis. We detail each of the architectures that are found in the literature along with their application scenarios, benchmark datasets, main results, and advantages, and then present the open challenges for CELM. We followed a well-structured methodology and established relevant research questions that guided our findings. Based on 81 primary studies, we found that object recognition is the most common problem that is solved by CELM, and CCN with predefined kernels is the most common CELM architecture proposed in the literature. The results from experiments show that CELM models present good precision, convergence, and computational performance, and they are able to decrease the total processing time that is required by the learning process. The results presented in this systematic review are expected to contribute to the research area of CELM, providing a good starting point for dealing with some of the current problems in the analysis of computer vision based on images.

show abstract

Section: Pre-trained Cnn In Other Application Domain For Feature Extraction and Elm For Fast Learningmentioning

confidence: 99%

Convolutional Extreme Learning Machines: A Systematic Review

et al. 2021

View full text Add to dashboard Cite

show abstract

“…We reported the use of VGG-16 [31], [68], [115], [69], [57], [66] and VGG-19 [100] architectures for extracting features and fine-tuning with ELM, all previously mentioned works used pre-trained weights from ILSVRC dataset. The work [83] presented an approach to predict and classify data using a multimodal approach, where video data (frame sequencing) and audio are considered.…”

Section: Pre-trained Cnn In Other Application Domain For Feature Extraction and Elm For Fast Learningmentioning

confidence: 99%

“…Inception-V3 is an evolution of the previous model containing regularization, grid size reduction and factorizing convolutions. Inception-V3 [126] is also considered a good alternative for transfer learning and has been considered in the literature for fine-tuning with ELM [31].…”

Section: Pre-trained Cnn In Other Application Domain For Feature Extraction and Elm For Fast Learningmentioning

confidence: 99%

“…ResNet uses a signal that is the sum of the signal produced by the two previous convolutional layers plus the signal transmitted directly from the point before these layers. We found some works that used ResNet for transfer learning using the pre-trained weights from ILSVRC dataset in conjunction with ELM: [31], [115], [100], [66], [96].…”

Section: Pre-trained Cnn In Other Application Domain For Feature Extraction and Elm For Fast Learningmentioning

confidence: 99%

See 1 more Smart Citation

Convolutional Extreme Learning Machines: A Systematic Review

Rodrigues¹,

Rogério²,

Kelner³

et al. 2021

Preprint

View full text Add to dashboard Cite

Many works have recently identified the need to combine deep learning with extreme learning to strike a performance balance with accuracy especially in the domain of multimedia applications. Considering this new paradigm, namely convolutional extreme learning machine (CELM), we present a systematic review that investigates alternative deep learning architectures that use extreme learning machine (ELM) for a faster training to solve problems based on image analysis. We detail each of the architectures found in the literature, application scenarios, benchmark datasets, main results, advantages, and present the open challenges for CELM. We follow a well structured methodology and establish relevant research questions that guide our findings. We hope that the observation and classification of such works can leverage the CELM research area providing a good starting point to cope with some of the current problems in the image-based computer vision analysis.

show abstract

“…Uno de los paradigmas del transfer learning es el fine-tuning del modelo, el cual busca adaptarlo a un nuevo dominio de aplicación [26]; para ello se toma el modelo previamente entrenado y se varían algunos parámetros como la tasa de aprendizaje, teniendo como objetivo lograr mejoras significativas en las predicciones [27].…”

Section: Figura 3 Validación Cruzada Con K-foldsunclassified

Transfer learning en la clasificación binaria de imágenes térmicas

2021

View full text Add to dashboard Cite

La clasificación de imágenes térmicas es un aspecto clave en el sector industrial, debido a que suele ser el punto de partida en la detección de fallos en equipos eléctricos. En algunos casos, esta tarea se automatiza mediante el uso de técnicas tradicionales de inteligencia artificial, mientras que en otros, es realizada de manera manual, lo cual puede traer consigo altas tasas de error humano. Este artículo presenta un análisis comparativo entre once arquitecturas de transfer learning (AlexNet, VGG16, VGG19, ResNet, DenseNet, MobileNet v2, GoogLeNet, ResNeXt, Wide ResNet, MNASNet y ShuffleNet) mediante el uso de fine-tuning, con la finalidad de realizar una clasificación binaria de imágenes térmicas en una red de distribución eléctrica. Para ello, se dispone de una base de datos con 815 imágenes, divididas mediante la técnica tipo hold-out 60-20-20 y validación cruzada con 5-folds, para finalmente analizar su rendimiento mediante el test de Friedman. Luego de los experimentos, se obtuvieron resultados satisfactorios con exactitudes superiores a 85 % en diez de las arquitecturas previamente entrenadas. Sin embargo, la arquitectura que no se entrenó previamente presentó una exactitud baja; concluyéndose que la aplicación de transfer learning mediante el uso de arquitecturas previamente entrenadas es un mecanismo adecuado en la clasificación de este tipo de imágenes, y representa una alternativa confiable frente a técnicas tradicionales de inteligencia artificial.

show abstract

Fine-Tuning of Pre-Trained Deep Learning Models with Extreme Learning Machine

Cited by 25 publications

References 15 publications

Convolutional Extreme Learning Machines: A Systematic Review

Convolutional Extreme Learning Machines: A Systematic Review

Convolutional Extreme Learning Machines: A Systematic Review

Transfer learning en la clasificación binaria de imágenes térmicas

Contact Info

Product

Resources

About