Deep Learning Models for Image Classification: Comparison and Applications

Sharma, Shagun; Guleria, Kalpna

doi:10.1109/icacite53722.2022.9823516

Cited by 66 publications

(9 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, DL, derived from research on artificial neural networks, has achieved significant progress in many fields, including computer vision, facial recognition, and image processing (50). Its success originates from its capability to extract higher-level features from raw data and classify information using multiple layers of information modules in a hierarchical structure (51).…”

Section: Lce Grids: Large-scale Real-time High-precision Stf Sensormentioning

confidence: 99%

Melt electrowriting enabled 3D liquid crystal elastomer structures for cross-scale actuators and temperature field sensors

Feng,

Wang,

Xue

et al. 2024

Sci. Adv.

View full text Add to dashboard Cite

Liquid crystal elastomers (LCEs) have garnered attention for their remarkable reversible strains under various stimuli. Early studies on LCEs mainly focused on basic dimensional changes in macrostructures or quasi–three-dimensional (3D) microstructures. However, fabricating complex 3D microstructures and cross-scale LCE-based structures has remained challenging. In this study, we report a compatible method named melt electrowriting (MEW) to fabricate LCE-based microfiber actuators and various 3D actuators on the micrometer to centimeter scales. By controlling printing parameters, these actuators were fabricated with high resolutions (4.5 to 60 μm), actuation strains (10 to 55%), and a maximum work density of 160 J/kg. In addition, through the integration of a deep learning–based model, we demonstrated the application of LCE materials in temperature field sensing. Large-scale, real-time, LCE grid–based spatial temperature field sensors have been designed, exhibiting a low response time of less than 42 ms and a high precision of 94.79%.

show abstract

Section: Lce Grids: Large-scale Real-time High-precision Stf Sensormentioning

confidence: 99%

Melt electrowriting enabled 3D liquid crystal elastomer structures for cross-scale actuators and temperature field sensors

Feng,

Wang,

Xue

et al. 2024

Sci. Adv.

View full text Add to dashboard Cite

show abstract

“…The VGG-16 architecture, also known as the Visual Geometry Group-16, is a deep learning model created by researchers at the University of Oxford [25]. This Convolutional Neural Network (CNN) is specifically designed for image recognition and classification tasks [26][27][28]. VGG-16 is renowned for its simplicity and relatively lower computational complexity compared to other deep learning architectures like ResNet and Inception [29].…”

Section: Description Of Vgg-16 Architecturementioning

confidence: 99%

Exploring the Potential of VGG-16 Architecture for Accurate Brain Tumor Detection Using Deep Learning

Gayathri

Dhavileswarapu

Ibrahim

et al. 2023

JCMM

View full text Add to dashboard Cite

This study explores the potential of the VGG-16 architecture, a Convolutional Neural Network (CNN) model, for accurate brain tumor detection through deep learning. Utilizing a dataset consisting of 1655 brain MRI images with tumors and 1598 images with- out tumors, the VGG-16 model was fine-tuned and trained on this data. Initial training achieved an accuracy of 91%, which was improved to 94% after hyperparameter optimization. The model’s sensitivity, specificity, precision, recall, and F1 scores were strong, indicating its potential in accurately detecting brain tumors. The performance of the VGG-16 model was compared to several other techniques for brain tumor detection, including EasyDL, GoogLeNet, GrayNet, ImageNet, CNN, and a Multivariable Regression and Neural Network model. Although it did not achieve the highest accuracy, it outperformed GoogLeNet and ImageNet and demon- strated comparable accuracy to GrayNet and the Multivariable Regression and Neural Network. Its sensitivity and specificity suggest its potential in identifying tumors that other methods might miss, reinforcing its potential usefulness in medical applications. Never- theless, there is room for improvement. Future studies could collect and annotate larger datasets to improve model generalizability. Exploring other deep learning architectures and enhancing model interpretability could further boost its clinical relevance. Despite these challenges, this study demonstrates the untapped potential of the VGG-16 architecture in brain tumor detection and contributes to the growing body of research on applying deep learning in the medical field.

show abstract

“…These classifiers utilize a pre-trained deep neural network as a foundation for a new task [34], allowing them to benefit from the pre-trained network's feature extraction abilities. This essentially results in a classifier that requires fewer training samples and exhibits faster convergence [5]. The discussion below on these classifiers brings a sense of the current state-of-the-art approaches in the field of deep transfer learning in image classification, setting up a framework for later discussion of deep transfer learning optimization techniques.…”

Section: Deep Transfer Learning Classifiersmentioning

confidence: 99%

“…Finally, in order to account for the non-linear properties of the network, we can apply a scaling and shifting operation to the original output, (5) The normalization of the input to each layer of the network is an essential part of the batch normalization technique. This normalization is carried out across a smaller batch of examples, which assists in lowering the impact of the data's noise as shown above.…”

Section: A Batch Normalization Techniquesmentioning

confidence: 99%

Deep Transfer Learning Optimization Techniques for Medical Image Classifcation - A Survey

Kariuki¹,

Gikunda²,

Wandeto³

2023

Preprint

View full text Add to dashboard Cite

<p>Medical image classification is not only a complex task but also a challenging one due to the heterogeneous nature of medical data. Deep transfer learning has proven to be a viable technique for medical image classification throughout the years, mostly because it is able to leverage knowledge from pre-trained models learned from large-scale datasets, improved performance, minimal training and overcoming the disadvantage of small data sets. This paper offers a succinct review of the cutting-edge deep transfer learning optimization approaches for medical image classification. The paper begins with an overview of convolutional neural networks (CNN) and transfer learning techniques, such as relation-based, feature, parameter and instance-based transfer learning. Then, the study examines classical classifiers, such as Resnet, VGG, Alexnet, Googlenet, and Inception, and compare their performance on medical image classification tasks. The study also presents optimization techniques, including batch normalization, regularization, and weight initialization, data augmentation and the kernel mathematical formulations. Finally, the study unearths various challenges that arise when using deep transfer learning for medical image classification as well as potential future approaches for this field.</p>

show abstract

Deep Learning Models for Image Classification: Comparison and Applications

Cited by 66 publications

References 19 publications

Melt electrowriting enabled 3D liquid crystal elastomer structures for cross-scale actuators and temperature field sensors

Melt electrowriting enabled 3D liquid crystal elastomer structures for cross-scale actuators and temperature field sensors

Exploring the Potential of VGG-16 Architecture for Accurate Brain Tumor Detection Using Deep Learning

Deep Transfer Learning Optimization Techniques for Medical Image Classifcation - A Survey

Contact Info

Product

Resources

About