-
[pdf]
[arXiv]
[bibtex]@InProceedings{Sirko-Galouchenko_2024_CVPR, author = {Sirko-Galouchenko, Sophia and Boulch, Alexandre and Gidaris, Spyros and Bursuc, Andrei and Vobecky, Antonin and P\'erez, Patrick and Marlet, Renaud}, title = {OccFeat: Self-supervised Occupancy Feature Prediction for Pretraining BEV Segmentation Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {4493-4503} }
OccFeat: Self-supervised Occupancy Feature Prediction for Pretraining BEV Segmentation Networks
Abstract
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.
Related Material