Dong Huang, Ph.D.

Links:

I work on Dense Supervision approaches for efficient deep learning perception:

1. Perception on embedded platforms: My research team at RI CMU empowers cameras and sensors on moving platforms-autonomous machines, drones, smart camera modules-with (a) the light-weight Deep Neural Networks (DNNs) that consume less computation, memory, and power than standard deep learning approaches, and (b) the advanced training approaches that improve performance on embedded platforms without overheads on deployment efforts, training data and testing computation. We are making intelligent perception solutions accessible for general industries and markets.

2. Perception in multi-modality systems: We develop deep learning approaches that take multiple sensor data (e.g., videos, depth, wearable sensor signal, and WiFi signal) to produce multiple perception results, such as location, poses, activities, and physical metrics. Our deep approaches also trace the key factors of perception results for the purpose of improving the psychical performance of athletes and quality-of-life for the general public.