Modeling
In modeling discussion, we will discuss two key aspects. 1. SOTA Segmentation Models: What are the state-of-the-art segmentation models and their architectures? 2. Transfer Learning: How can you use these models to train a better segmenter for the self-driving car data?
SOTA segmentation models
Machine learning in general and deep learning, in particular, have progressed a lot in the domain of computer vision-based applications during the last decade. The models enlisted in this section are the most commonly used deep neural networks that provide state-of-the-art (SOTA) results for object detection and segmentation tasks. These tasks form the basis for the self-driving car use case.
FCN
Fully convolutional networks (FCNs) are one of the top-performing networks for semantic segmentation tasks.
đź“ť Segmentation is a dense prediction task of pixel-wise classification.
A typical FCN operates by fine-tuning an image classification CNN and applying pixel-wise training. It first compresses the information using multiple layers of convolutions and pooling. Then, it up-samples these feature maps to predict each pixel’s class from this compressed information.