Bayesian Prediction of Future Street Scenes using Synthetic Likelihoods

Understand

For autonomous agents to successfully operate in the real world, the ability to anticipate future scene states is a key competence.

• In real-world scenarios, future states become increasingly uncertain and multi-modal, particularly on long time horizons.
• Dropout based Bayesian inference provides a computationally tractable, theoretically well grounded approach to learn likely hypotheses/models to deal with uncertain futures and make predictions that correspond well to observations -- are well calibrated.
• However, it turns out that such approaches fall short to capture complex real-world scenes, even falling behind in accuracy when compared to the plain deterministic approaches.