AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Domain Adaptive Semantic Segmentation Using Weak Labels

Sujoy Paul, Yi-Hsuan Tsai, Samuel Schulter, Amit K. Roy-Chowdhury, Manmohan Chandraker

ECCV 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 90 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 weak-label classification loss L_c (pseudo-weak) to output-space alignment baseline (ablation)AdaptOutput baseline · GTA5 -> Cityscapes (no pixel-level adaptation)mIoU (%): 41.4 -> 44.2Improved
add category-wise alignment L_adv on top of L_c (pseudo-weak) (ablation)Ours (UDA) · GTA5 -> Cityscapes (no pixel-level adaptation)mIoU (%): 44.2 -> 45.6Improved
add category-wise alignment L_adv on top of L_c (oracle-weak) (ablation)Ours (WDA) · GTA5 -> Cityscapes (no pixel-level adaptation)mIoU (%): 50.8 -> 52.1Improved
add category-wise alignment L_adv on top of L_c (pseudo-weak) (ablation)Ours (UDA) · SYNTHIA -> Cityscapes (16 classes) (no pixel-level adaptation)mIoU (%): 41.7 -> 42.7Improved
add category-wise alignment L_adv on top of L_c (oracle-weak) (ablation)Ours (WDA) · SYNTHIA -> Cityscapes (16 classes) (no pixel-level adaptation)mIoU (%): 47.8 -> 49.2Improved
add pixel-level adaptation to full pseudo-weak method (ablation)Ours (UDA) · GTA5 -> CityscapesmIoU (%): 45.6 -> 48.2Improved
add pixel-level adaptation to full oracle-weak method (ablation)Ours (WDA: Image) · GTA5 -> CityscapesmIoU (%): 52.1 -> 53.0Improved
use oracle-weak labels instead of pseudo-weak labelsOurs · GTA5 -> Cityscapes (no pixel-level adaptation)mIoU (%): 45.6 -> 52.1Improved
use point supervision instead of image-level oracle-weak labelsOurs (WDA) · GTA5 -> CityscapesmIoU (%): 53.0 -> 56.4Improved
use point supervision instead of image-level oracle-weak labelsOurs (WDA) · SYNTHIA -> Cityscapes (16 classes)mIoU (%): 50.6 -> 57.2Improved
use 5-point supervision instead of image-level labelsOurs (WDA) · GTA5 -> CityscapesmIoU (%): 59.4 vs 65.1 fully supervisedImproved
raise pseudo-weak label threshold T above 0.3 (ablation)Ours (UDA) · GTA5 -> CityscapesmIoU (%)Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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