AI Paper Atlas

Research map / Benchmarks / SYNTHIA → Cityscapes

SYNTHIA → Cityscapes leaderboard

46 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on SYNTHIA → Cityscapes. Best mIoU: 73.5 (GANDA, AAAI 2023).

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.

SYNTHIA → Cityscapes · mIoU

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

#mIoU ↑MethodPaperTopic
173.5GANDAGeometry-Aware Network for Domain Adaptive Semantic Segmentation
AAAI 2023 · Table 2
Segmentation and detection
268.1MADA (M4)Multi-Anchor Active Domain Adaptation for Semantic Segmentation
ICCV 2021 · Table 3
Domain adaptation and generalization
367.7IR2F-RMM
HRDA, MiT-B5
Continuous Pseudo-Label Rectified Domain Adaptive Semantic Segmentation With Implicit Neural Representations
CVPR 2023 · Table 1
Domain adaptation and generalization
467FREDOM (Transformer)
Transformer
FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding
CVPR 2023 · Comparison with SOTA Approache
Domain adaptation and generalization
566.8ProDA + BDM
ProDA
Bidirectional Domain Mixup for Domain Adaptive Semantic Segmentation
AAAI 2023 · Table: Comparison with state-o
Domain adaptation and generalization
656.6CVRN
DeepLab-V2
Cross-View Regularization for Domain Adaptive Panoptic Segmentation
CVPR 2021 · Table: SYNTHIA → Cityscapes Se
Open-set and few-shot detection
754.1Ours
DeepLab-V2 with ResNet-101
Cross-Domain Grouping and Alignment for Domain Adaptive Semantic Segmentation
AAAI 2021 · Table: Quantitative results on
Domain adaptation and generalization
853.6CaCo
DeepLab-V2 with ResNet101
Category Contrast for Unsupervised Domain Adaptation in Visual Tasks
CVPR 2022 · Table 2
Domain adaptation and generalization
953.4CLOUDS
ConvNeXt-L
Collaborating Foundation Models for Domain Generalized Semantic Segmentation
CVPR 2024 · Table 2
Open-set and few-shot detection
1053I2VDAIs It Necessary to Transfer Temporal Knowledge for Domain Adaptive Video Semantic Segmentation?
ECCV 2022 · Table 2
Domain adaptation and generalization
23 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

SYNTHIA → Cityscapes · mIoU (val)

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

#mIoU ↑MethodPaperTopic
172.7D2ADA (5% labels)
DeepLabV3+
D2ADA: Dynamic Density-Aware Active Domain Adaptation for Semantic Segmentation
ECCV 2022 · Table 1
Domain adaptation and generalization
270.1RIPU (RA, 2.2%)
DeepLab-v2
Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentation
CVPR 2022 · Table 2
Domain adaptation and generalization
369MIC + ECOCSeg
MIT-B5
Towards Robust Pseudo-Label Learning in Semantic Segmentation: An Encoding Perspective
NeurIPS 2025 · Table 1
Semi-supervised learning
467.9MIC_HRDA + MICDrop
MiT-B5 (SegFormer)
MICDrop: Masking Image and Depth Features via Complementary Dropout for Domain-Adaptive Semantic Segmentation
ECCV 2024 · Table 1
Domain adaptation and generalization
567.3MIC (HRDA)
DAFormer
MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation
CVPR 2023 · Semantic segmentation table
Domain adaptation and generalization
665.3CPSL+distill
CPSL
Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentation
CVPR 2022 · Table: SYNTHIA → Cityscapes re
Domain adaptation and generalization
755.9DTST + SND
DeepLab-v2, ResNet-101
Stable Neighbor Denoising for Source-free Domain Adaptive Segmentation
CVPR 2024 · Table 1
Domain adaptation and generalization
853.9Ours
DeepLab v2, ResNet-101
Unsupervised Domain Adaptation for Semantic Segmentation by Content Transfer
AAAI 2021 · Table 2
Domain adaptation and generalization
947.3Ours
DeepLabV2-Res101
Style Mixing and Patchwise Prototypical Matching for One-Shot Unsupervised Domain Adaptive Semantic Segmentation
AAAI 2022 · Table 2
Domain adaptation and generalization
1046.7Ours (multi-level)
ResNet-101
Learning to Adapt Structured Output Space for Semantic Segmentation
CVPR 2018 · Table 4
Domain adaptation and generalization
3 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.