Papers › Three Ways to Improve Semantic Segmentation with Self-Supervised Depth Estimation
Three Ways to Improve Semantic Segmentation with Self-Supervised Depth Estimation
Lukas Hoyer, Dengxin Dai, Yuhua Chen, Adrian Köring, Suman Saha, Luc van Gool
Training deep networks for semantic segmentation requires large amounts of labeled training data, which presents a major challenge in practice, as labeling segmentation masks is a highly labor-intensive process. To address this issue, we present a framework for semi-supervised semantic segmentation, which is enhanced by self-supervised monocular depth estimation from unlabeled image sequences. In particular, we propose three key contributions: (1) We transfer knowledge from features learned during self-supervised depth estimation to semantic segmentation, (2) we implement a strong data augmentation by blending images and labels using the geometry of the scene, and (3) we utilize the depth feature diversity as well as the level of difficulty of learning depth in a student-teacher framework to select the most useful samples to be annotated for semantic segmentation. We validate the proposed model on the Cityscapes dataset, where all three modules demonstrate significant performance gains, and we achieve state-of-the-art results for semi-supervised semantic segmentation. The implementation is available at https://github.com/lhoyer/improving_segmentation_with_selfsupervised_depth.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Semi-Supervised Semantic Segmentation | Cityscapes 100 samples labeled | SegSDE (MTL decoder with ResNet101, ImageNet pretrained, unlabeled image sequences) | Validation mIoU | 62.09% | #5 of 13 | Archive leaderboard | report |
| Semi-Supervised Semantic Segmentation | Cityscapes 12.5% labeled | SegSDE (MTL decoder with ResNet101, ImageNet pretrained, unlabeled image sequences) | Validation mIoU | 68.01% | #23 of 33 | Archive leaderboard | report |
| Semi-Supervised Semantic Segmentation | Cityscapes 25% labeled | SegSDE (MTL decoder with ResNet101, ImageNet pretrained, unlabeled image sequences) | Validation mIoU | 69.38% | #21 of 30 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
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