Bayesian Prediction of Future Street Scenes using Synthetic Likelihoods

TL;DR

This paper introduces a Bayesian method using synthetic likelihoods to improve multi-modal future scene prediction, achieving state-of-the-art accuracy and better calibration in diverse tasks.

Contribution

It presents a novel Bayesian formulation leveraging synthetic likelihoods to enhance diversity and accuracy in future scene state predictions.

Findings

Achieves state-of-the-art accuracy on Cityscapes scene anticipation.

Provides well-calibrated probability estimates.

Generalizes effectively to tasks like digit generation and precipitation forecasting.

Abstract

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. This is because the used log-likelihood estimate discourages diversity. In this work, we propose a novel Bayesian formulation for anticipating future scene states which leverages synthetic likelihoods that encourage the learning of diverse models to accurately capture the multi-modal nature of future scene states. We show that our approach achieves accurate state-of-the-art predictions and calibrated probabilities through extensive experiments for scene anticipation on Cityscapes dataset. Moreover, we show that our approach generalizes across diverse tasks such as digit generation and precipitation forecasting.