AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Improving Semi-Supervised and Domain-Adaptive Semantic Segmentation with Self-Supervised Depth Estimation

Lukas Hoyer, Dengxin Dai, Qin Wang, Yuhua Chen, Luc Van Gool

IJCV 2023 · Label-efficient and robust learning › Semi-supervised learning · approach: Consistency training for semi-supervised segmentation · 57 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add DepthMix instead of ClassMix (ablation)semi-supervised segmentation · Cityscapes (372 labels)mIoU (%): 63.16 -> 64.14Improved
add DepthMix instead of ClassMix (ablation)semi-supervised segmentation · Cityscapes (2975 labels)mIoU (%): 69.60 -> 69.83Improved
add mean-teacher pseudo-labels (ablation)baseline · Cityscapes (372 labels)mIoU (%): 59.14 -> 62.39Improved
add DepthMix on top of pseudo-labels (ablation)pseudo-label baseline · Cityscapes (372 labels)mIoU (%): 62.39 -> 64.14Improved
add SDE transfer learning of encoder and decoder (ablation)baseline · Cityscapes (372 labels)mIoU (%): 59.14 -> 60.46Improved
add ImageNet feature distance loss to SDE pretraining (ablation)SDE transfer · Cityscapes (372 labels)mIoU (%): 60.46 -> 60.80Improved
add multi-task learning to transfer (ablation)SDE transfer + F · Cityscapes (372 labels)mIoU (%): 60.80 -> 61.25Improved
add diversity plus uncertainty sampling instead of diversity only (ablation)automatic data selection · Cityscapes (100 labels)mIoU (%): 53.00 -> 54.37Improved
diversity vs uncertainty sampling at few labels (ablation)automatic data selection · Cityscapes (100 labels)mIoU (%): 53.00 vs 51.75Mixed
uncertainty sampling beats diversity with more labels (ablation)automatic data selection · Cityscapes (744 labels)mIoU (%): 66.76 vs 66.37Mixed
add depth-based DS+US selection instead of entropy active learningrandom baseline · Cityscapes (372 labels)mIoU (%): 63.51 -> 64.25Improved
add data selection to DepthMix+MTL (ablation)DepthMix+MTL · Cityscapes (372 labels)mIoU (%): 66.66 -> 68.01Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy