Original article was published by Sik-Ho Tsang on Artificial Intelligence on Medium
Reading: ENet — Real-Time Semantic Segmentation (Semantic Segmentation)
Comparable Results But Much Smaller Size & Faster Inference Time Than SegNet
In this story, “ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation” (ENet), by Purdue University, is presented. “Real-time” is important for applications, such as autonomous driving, that cannot be done offline. In this paper:
- A novel deep neural network architecture named ENet (efficient neural network), is created specifically for tasks requiring low latency operation.
- ENet is up to 18 faster, requires 75 less FLOPs, has 79 less parameters, and provides similar or better accuracy to existing models.
This is a paper in 2016 arXiv with over 700 citations. (Sik-Ho Tsang @ Medium)