Modern deep learning has enabled amazing developments of computer vision in recent years. As a fundamental task, semantic segmentation aims to predict class labels for each pixel of images, which empowers machines perception of the visual world. In spite of recent successes of fully convolutional networks, several challenges remain to be addressed. In this work, we focus on this topic, under different kinds of input formats and various types of scenes. Specifically, our study contains two aspects:
(1) Data-driven neural modules for improved performance.
(2) Leverage of datasets w.r.t. training systems with higher performances and better data privacy guarantees.