Research Progress and Application of Lightweight Neural Networks

Speaker:  Junying Chen – Guangzhou, China
Topic(s):  Artificial Intelligence, Machine Learning, Computer Vision, Natural language processing


Convolutional neural networks (CNNs) have achieved unmatched performance in many applications such as image classification, object detection, and semantic segmentation. Current research trend of improving and enhancing network performance makes the networks deeper and more complex, which eventually leads to a dramatic increase in the model size and the required computational resources. Due to these two reasons, most modern CNN models can only run on servers equipped with high-performance GPUs. Although embedded devices and mobile platforms have a huge demand for deployment of deep models, current architectures are not suitable for these systems due to their limited memory, power, and computational resources. Therefore, designing lightweight yet accurate CNN models that can be deployed in embedded devices and mobile platforms has become an active research direction. This lecture will introduce the research progress of lightweight neural networks, and the applications of lightweight neural networks to image and video analysis.

About this Lecture

Number of Slides:  30
Duration:  40 minutes
Languages Available:  Chinese (Simplified), English
Last Updated: 

Request this Lecture

To request this particular lecture, please complete this online form.

Request a Tour

To request a tour with this speaker, please complete this online form.

All requests will be sent to ACM headquarters for review.