Copy-Pasting Coherent Depth Regions Improves Contrastive Learning for Urban-Scene Segmentation
Liang Zeng (Delft University of Technology), Attila Lengyel (Delft University of Technology), Nergis Tomen (Delft University of Technology), Jan C van Gemert (Delft University of Technology)*
The 33rd British Machine Vision Conference
Best Student Paper Award Honourable Mention
Abstract
In this work, we leverage estimated depth to boost self-supervised contrastive learning for segmentation of urban scenes, where unlabeled videos are readily available for training self-supervised depth estimation. We argue that the semantics of a coherent group of pixels in 3D space is self-contained and invariant to the contexts in which they appear. We group coherent, semantically related pixels into coherent depth regions given their estimated depth and use copy-paste to synthetically vary their contexts. In this way, cross-context correspondences are built in contrastive learning and a context-invariant representation is learned. For unsupervised semantic segmentation of urban scenes, our method surpasses the previous state-of-the-art baseline by +7.14% in mIoU on Cityscapes and +6.65% on KITTI. For fine-tuning on Cityscapes and KITTI segmentation, our method is competitive with existing models, yet, we do not need to pre-train on ImageNet or COCO, while we are also more computationally efficient. Our code is available on https://github.com/LeungTsang/CPCDR.Video
Citation
@inproceedings{Zeng_2022_BMVC,
author = {Liang Zeng and Attila Lengyel and Nergis Tomen and Jan C van Gemert},
title = {Copy-Pasting Coherent Depth Regions Improves Contrastive Learning for Urban-Scene Segmentation},
booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
publisher = {{BMVA} Press},
year = {2022},
url = {https://bmvc2022.mpi-inf.mpg.de/0893.pdf}
}
Copyright © 2022
The British Machine Vision Conference is organised by