Papers › Copy-Pasting Coherent Depth Regions Improves Contrastive Learning for Urban-Scene Segmentation

Copy-Pasting Coherent Depth Regions Improves Contrastive Learning for Urban-Scene Segmentation

25 Nov 2022arXiv:2211.14074archive 2025-07-28

Liang Zeng, Attila Lengyel, Nergis Tömen, Jan van Gemert

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, and we are also more computationally efficient. Our code is available on https://github.com/LeungTsang/CPCDR

PaperPDFCode

Code

leungtsang/cpcdr officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Contrastive LearningDepth EstimationScene SegmentationSegmentationSemantic SegmentationUnsupervised Semantic Segmentation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Contrastive LearningCopy-Paste

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections