What question did this study set out to answer?

Evaluate and compare the real-time classification and object detection capabilities of AlexNet, GoogLeNet, and ResNet50 across multiple image benchmarks and video feeds.

January 1, 2018Procedia Computer ScienceOpen Access

An Analysis Of Convolutional Neural Networks For Image Classification

View Full Paper

Ask AI

Bookmark

Evaluate and compare the real-time classification and object detection capabilities of AlexNet, GoogLeNet, and ResNet50 across multiple image benchmarks and video feeds.
Benchmarked three convolutional neural network architectures—AlexNet, GoogLeNet, and ResNet50—using ImageNet, CIFAR-10, and CIFAR-100 datasets.
Evaluated trained networks on real-time video feeds as testing datasets to assess practical performance across diverse object categories.
GoogLeNet and ResNet50 achieve higher object recognition precision compared to AlexNet.
Object classification precision varies substantially across different categories of objects across all tested architectures.

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

Comparative analysis demonstrates superior precision of GoogLeNet and ResNet50 in video feeds, highlighting structural performance advantages in deeper network architectures.

Cite This Study

Sharma et al. (2018) studied this question.

synapsesocial.com/papers/69dab2bf8988aeabbe68763b https://doi.org/10.1016/j.procs.2018.05.198

View Full Paper

Ask AI

Bookmark

Implication

Comparative analysis demonstrates superior precision of GoogLeNet and ResNet50 in video feeds, highlighting structural performance advantages in deeper network architectures.

An Analysis Of Convolutional Neural Networks For Image Classification

Key Points

Discussion

Implication

Cite This Study

An Analysis Of Convolutional Neural Networks For Image Classification

Key Points

Discussion

Implication

Cite This Study

Also Consider

Also Consider