Image Enhancement and Classification of CIFAR-10 Using Convolutional Neural Networks

Divya, S.; Adepu, Bhaskar; Kamakshi, P.

doi:10.1109/icssit53264.2022.9716555

Cited by 7 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It implies that in other systems, which are traditionally manually designed, the network knows about filters. Because of the lower restriction on prior knowledge, CNN has a major benefit over others, and designing hand-engineered characteristics is difficult [13], [14], [28].…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Classification on Unsupervised Deep Hashing With Pseudo Labels Using Support Vector Machine for Scalable Image Retrieval

Sharma

Rai

Sharma

2023

WJCMS

View full text Add to dashboard Cite

The content-based image retrieval (CBIR) method operates on the low-level visual features of the user input query object, which makes it difficult for users to formulate the query and also does not provide adequate retrieval results. In the past, image annotation was suggested as the best possible framework for CBIR, which works on automatically signing keywords to images that support image retrieval. The recent successes of deep learning techniques, especially Convolutional Neural Networks (CNN), in solving computer vision applications have inspired me to work on this paper to solve the problem of CBIR using a dataset of annotated images

show abstract

Section: Methodsmentioning

confidence: 99%

“…The muddle codes greatly minimize the need for extra room to improve mathematical abilities [8], [9]. As of late, many hashing methods [10][11][12][13] have carried out impressive executions.…”

Section: Introductionmentioning

confidence: 99%

Classification on Unsupervised Deep Hashing With Pseudo Labels Using Support Vector Machine for Scalable Image Retrieval

Sharma

Rai

Sharma

2023

WJCMS

View full text Add to dashboard Cite

show abstract

“…Han et al [16] employed a pruning technique to reduce the size of networks in AlexNet [17] [20] by 9x without compromising accuracy in image classification. Similarly, Li et al [21] utilized filter pruning techniques to lower inference costs for DNN models, such as VGG-16 [22] and residual network (ResNet)-110 [23], on the CIFAR10 [24] image classification dataset. Despite its benefits, pruning the DNN architecture can result in accuracy loss and introduce complexity during model training.…”

Section: Introductionmentioning

confidence: 99%

Deep neural networks optimization for resource-constrained environments: techniques and models

Careem,

Md Johar,

Khatibi

2024

IJEECS

View full text Add to dashboard Cite

This paper aims to present a comprehensive review of advanced techniques and models with a specific focus on deep neural network (DNN) for resource-constrained environments (RCE). The paper contributes by highlighting the RCE devices, analyzing challenges, reviewing a broad range of optimization techniques and DNN models, and offering a comparative assessment. The findings provide potential optimization techniques and recommend a baseline model for future development. It encompasses a broad range of DNN optimization techniques, including network pruning, weight quantization, knowledge distillation, depthwise separable convolution, residual connections, factorization, dense connections, and compound scaling. Moreover, the review analyzes the established optimization models which utilizes the above optimization techniques. A comprehensive analysis is conducted for each technique and model, considering its specific attributes, usability, strengths, and limitations in the context of effective deployment in RCEs. The review also presents a comparative assessment of advanced DNN models’ deployment for image classification, employing key evaluation metrics such as accuracy and efficiency factors like memory and inference time. The article concludes with the finding that combining depthwise separable convolution, weight quantization, and pruning represents potential optimization techniques, while also recommending EfficientNetB1 as a baseline model for the future development of optimization models in RCE image classification.<p> </p>

show abstract

Deep Learning-Based Weight Initialization on Multi-layer Perceptron for Image Recognition

Mukherjee

Dey

2023

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Image Enhancement and Classification of CIFAR-10 Using Convolutional Neural Networks

Cited by 7 publications

References 12 publications

Classification on Unsupervised Deep Hashing With Pseudo Labels Using Support Vector Machine for Scalable Image Retrieval

Classification on Unsupervised Deep Hashing With Pseudo Labels Using Support Vector Machine for Scalable Image Retrieval

Deep neural networks optimization for resource-constrained environments: techniques and models

Deep Learning-Based Weight Initialization on Multi-layer Perceptron for Image Recognition

Contact Info

Product

Resources

About