Can I read Adaptive Deep Learning for Soft Real-Time Image Classification on EtoBox?

Adaptive Deep Learning for Soft Real-Time Image Classification by Chai, Fangming (author);Kang, Kyoung-Don (author) is a Engineering article available to read on EtoBox.

What is Adaptive Deep Learning for Soft Real-Time Image Classification about?

CNNs (Convolutional Neural Networks) are becoming increasingly important for real-time applications, such as image classification in traffic control, visual surveillance, and smart manufacturing. It is challenging, however, to meet timing constraints of image processing tasks using CNNs due to their complexity. Performing dynamic trade-offs between the inference accuracy and time for image data analysis in CNNs is challenging too, since we observe that more complex CNNs that take longer to run even lead to lower accuracy in many cases by evaluating hundreds of CNN models in terms of time and accuracy using two popular data sets, MNIST and CIFAR-10. To address these challenges, we propose a new approach that (1) generates CNN models and analyzes their average inference time and accuracy for image classification, (2) stores a small subset of the CNNs with monotonic time and accuracy relationships offline, and (3) efficiently selects an effective CNN expected to support the highest possible accuracy among the stored CNNs subject to the remaining time to the deadline at run time. In our extensive evaluation, we verify that the CNNs derived by our approach are more flexible and cost-eff

Who reads Adaptive Deep Learning for Soft Real-Time Image Classification?

Author

Chai, Fangming (author);Kang, Kyoung-Don (author)

Publisher

MDPI AG

Published

2021

Language

EN

Field

Engineering (Physical Sciences)