Forecast-MAE: Self-supervised Pre-training for Motion Forecasting with Masked Autoencoders

TL;DR

Forecast-MAE introduces a self-supervised learning framework using masked autoencoders for motion forecasting, leveraging agent and road network interconnections, achieving competitive results without heavy supervision.

Contribution

It presents a novel self-supervised pre-training method for motion forecasting using mask autoencoders tailored for trajectory and road network data.

Findings

Outperforms previous self-supervised methods significantly.

Achieves competitive performance with state-of-the-art supervised models.

Utilizes minimal inductive bias with standard Transformer architecture.

Abstract

This study explores the application of self-supervised learning (SSL) to the task of motion forecasting, an area that has not yet been extensively investigated despite the widespread success of SSL in computer vision and natural language processing. To address this gap, we introduce Forecast-MAE, an extension of the mask autoencoders framework that is specifically designed for self-supervised learning of the motion forecasting task. Our approach includes a novel masking strategy that leverages the strong interconnections between agents' trajectories and road networks, involving complementary masking of agents' future or history trajectories and random masking of lane segments. Our experiments on the challenging Argoverse 2 motion forecasting benchmark show that Forecast-MAE, which utilizes standard Transformer blocks with minimal inductive bias, achieves competitive performance compared to state-of-the-art methods that rely on supervised learning and sophisticated designs. Moreover, it outperforms the previous self-supervised learning method by a significant margin. Code is available at https://github.com/jchengai/forecast-mae.