“Compound CNNs for Improved Classification Accuracy,” a Presentation from Southern Illinois University Carbondale

Spyros Tragoudas, Professor and School Director of Southern Illinois University Carbondale, presents the “Compound CNNs for Improved Classification Accuracy” tutorial at the May 2022 Embedded Vision Summit.

In this talk, Tragoudas presents a novel approach to improving the accuracy of convolutional neural networks (CNNs) used for classification. The approach utilizes the confusion matrix of the original CNN on a specific dataset to identify sets of low accuracy classes that resemble each other with respect to the error distribution. Using this information, several shallow networks are generated which operate in parallel with each other and evaluate input frames before the frames reach the original, large CNN.

The shallow networks are able to classify the low-accuracy classes more accurately than the original network, while eliminating the need to run the larger network on certain images. Hence, by combining the shallow networks with the original network, accuracy is improved, with virtually no increase in inference time.

See here for a PDF of the slides.

Here you’ll find a wealth of practical technical insights and expert advice to help you bring AI and visual intelligence into your products without flying blind.

Contact

Address

Berkeley Design Technology, Inc.
PO Box #4446
Walnut Creek, CA 94596

Phone
Phone: +1 (925) 954-1411
Scroll to Top