We introduce a self-supervised pretraining method, called OccFeat, for camera-only Bird's-Eye-View (BEV) segmentation networks. With OccFeat, we pretrain a BEV network via occupancy prediction and feature distillation tasks. Occupancy prediction provides a 3D geometric understanding of the scene to the model. However, the geometry learned is class-agnostic. Hence, we add semantic information to the model in the 3D space through distillation from a self-supervised pretrained image foundation model. Models pretrained with our method exhibit improved BEV semantic segmentation performance, particularly in low-data scenarios. Moreover, empirical results affirm the efficacy of integrating feature distillation with 3D occupancy prediction in our pretraining approach. Repository: https://github.com/valeoai/Occfeat
@article{arxiv.2404.14027,
title = {OccFeat: Self-supervised Occupancy Feature Prediction for Pretraining BEV Segmentation Networks},
author = {Sophia Sirko-Galouchenko and Alexandre Boulch and Spyros Gidaris and Andrei Bursuc and Antonin Vobecky and Patrick Pérez and Renaud Marlet},
journal= {arXiv preprint arXiv:2404.14027},
year = {2024}
}
Comments
Accepted to CVPR 2024, Workshop on Autonomous Driving