cfaed Seminar Series

Abstract

In this talk, we will focus on a general strategy and its application for pose estimation:

Sampling a pool of hypotheses, to serve as basis for a search. We will look at two approaches for training the search methods in this setting:

The first approach ranks hypotheses by learning to compare observed and synthesized images in a probabilistic formulation. It delivers strong improvements in accuracy especially in situations with heavy occlusion. The second approach goes a step further. We train an algorithm in the form of a reinforcement learning (RL) agent. The RL agent manipulates the hypothesis pool, by iteratively choosing hypotheses for refinement before making a final decision. We believe that RL can play an important role as a tool to learning complex algorithmic pipelines, especially in situations with a limited computational budget.

Everybody is welcome!