AI Paper Atlas

Research map / Benchmarks / GTA5 to Cityscapes

GTA5 to Cityscapes leaderboard

19 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on GTA5 to Cityscapes. Best mIoU: 59.3 (Ours+ProDA, CVPR 2022).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

GTA5 to Cityscapes · mIoU

19 papers, each with its best reported number for its own method; higher is better.

#mIoU ↑MethodPaperTopic
159.3Ours+ProDA
ResNet-101
Undoing the Damage of Label Shift for Cross-Domain Semantic Segmentation
CVPR 2022 · Table 1
Domain adaptation and generalization
256.6CorDA
ResNet-101
Domain Adaptive Semantic Segmentation With Self-Supervised Depth Estimation
ICCV 2021 · Table 3
Domain adaptation and generalization
353CLS + self-training (IAST group)
ResNet-101
Adversarial Unsupervised Domain Adaptation With Conditional and Label Shift: Infer, Align and Iterate
ICCV 2021 · Table 2
Domain adaptation and generalization
452.2IAST-MST
DeepLab-v2 ResNet-101
Instance Adaptive Self-Training for Unsupervised Domain Adaptation
ECCV 2020 · Table 5
Domain adaptation and generalization
550.5Ours
ResNet-101
Phase Consistent Ecological Domain Adaptation
CVPR 2020 · GTA5-to-Cityscapes results tab
Domain adaptation and generalization
650.3PixMatch (Augmentations) + MaxSquare
DeepLab-v2, ResNet-101
PixMatch: Unsupervised Domain Adaptation via Pixelwise Consistency Training
CVPR 2021 · Table 1
Domain adaptation and generalization
749.8MRKLD-SP-MST
ResNet-38
Confidence Regularized Self-Training
ICCV 2019 · Table 3
Domain adaptation and generalization
849.5Ours
DeepLab-ResNet101
Label-Driven Reconstruction for Domain Adaptation in Semantic Segmentation
ECCV 2020 · Table 1
Domain adaptation and generalization
947.5LSE + FL (ours)
ResNet101
Learning from Scale-Invariant Examples for Domain Adaptation in Semantic Segmentation
ECCV 2020 · Table 1
Domain adaptation and generalization
1047CBST-SP+MST
ResNet-38
Unsupervised Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training
ECCV 2018 · Table 3
Domain adaptation and generalization
9 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.