Pages Navigation Menu

News, Analysis & Perspective on Autonomous Vehicles

DeepVoting: A robust and explainable Deep Network for semantic part detection under Partial Occlusion

Baidu Research US, March 29, 2018

In this paper, we study the task of detecting semantic parts of an object, e.g., a wheel of a car, under partial occlusion. We propose that all models should be trained without seeing occlusions while being able to transfer the learned knowledge to deal with occlusions

Would you like to receive regular updates on new links?

Your Email