AI Paper Atlas

Research map / Benchmarks / GTA5->Cityscapes

GTA5->Cityscapes leaderboard

77 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on GTA5->Cityscapes. Best mIoU: 77.5 (MIC + MRM, CVPR 2026).

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->Cityscapes · mIoU

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

#mIoU ↑MethodPaperTopic
177.5MIC + MRMMasked Representation Modeling for Domain-Adaptive Segmentation
CVPR 2026 · Table 1
Domain adaptation and generalization
276.7T2S-DA (w/ MIC)
MIC
Pulling Target to Source: A New Perspective on Domain Adaptive Semantic Segmentation
IJCV 2024 · Table 4
Domain adaptation and generalization
374.9HRDA + BLV
HRDA
Balancing Logit Variation for Long-Tailed Semantic Segmentation
CVPR 2023 · Table 3
Open-set and few-shot detection
474.7HRDA + RTea
HRDA
Learning Pseudo-Relations for Cross-domain Semantic Segmentation
ICCV 2023 · Table 1
Domain adaptation and generalization
574.5GANDAGeometry-Aware Network for Domain Adaptive Semantic Segmentation
AAAI 2023 · Table 1
Segmentation and detection
673.6FREDOM (Transformer)
Transformer
FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding
CVPR 2023 · Comparison with SOTA Approache
Domain adaptation and generalization
769.1QueryDiff
DINOv2-L
Better to Teach than to Give: Domain Generalized Semantic Segmentation via Agent Queries with Diffusion Model Guidance
ICML 2025 · Table 1
Open-set and few-shot detection
869.1Ours (coarse label)
DeepLabv2 ResNet-101
Weakly-Supervised Domain Adaptive Semantic Segmentation With Prototypical Contrastive Learning
CVPR 2023 · Table 1
Domain adaptation and generalization
969.04DepthForge
DINOv2-L
Stronger, Steadier & Superior: Geometric Consistency in Depth VFM Forges Domain Generalized Semantic Segmentation
ICCV 2025 · Table 3
Domain adaptation and generalization
1068.88tqdm
EVA02-L (EVA02-CLIP)
Textual Query-Driven Mask Transformer for Domain Generalized Segmentation
ECCV 2024 · Table 1
Open-set and few-shot detection
54 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

GTA5->Cityscapes · mIoU (val)

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

#mIoU ↑MethodPaperTopic
171.3D2ADA (5% labels)
DeepLabV3+
D2ADA: Dynamic Density-Aware Active Domain Adaptation for Semantic Segmentation
ECCV 2022 · Table 1
Domain adaptation and generalization
268.3DAFormer
MiT-B5
DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation
CVPR 2022 · Table: Comparison with state-o
Domain adaptation and generalization
362.7DDB
ResNet-101, DeepLabv2
Deliberated Domain Bridging for Domain Adaptive Semantic Segmentation
NeurIPS 2022 · Table 2
Domain adaptation and generalization
460.8CPSL+distill
CPSL
Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentation
CVPR 2022 · Table: GTA5 → Cityscapes resul
Domain adaptation and generalization
558.1DTST + SND
DeepLab-v2, ResNet-101
Stable Neighbor Denoising for Source-free Domain Adaptive Segmentation
CVPR 2024 · Table 1
Domain adaptation and generalization
657.5ProDA
DeepLabv2, ResNet-101
Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation
CVPR 2021 · Table 1
Domain adaptation and generalization
757.1Ours
DeepLab-V2 ResNet-101
Bi-directional Contrastive Learning for Domain Adaptive Semantic Segmentation
ECCV 2022 · Table 1
Domain adaptation and generalization
856.5HIAST + HCSP (Ours)
DeepLab-v2
Heuristic Self-Paced Learning for Domain Adaptive Semantic Segmentation under Adverse Conditions
CVPR 2026 · Table 5
Domain adaptation and generalization
953.3DPL-Dual
DeepLab-V2 ResNet101
Dual Path Learning for Domain Adaptation of Semantic Segmentation
ICCV 2021 · Table 4
Domain adaptation and generalization
1050.2CAG-UDA
DeepLab v2 / ResNet-101
Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation
NeurIPS 2019 · Table 1
Domain adaptation and generalization
6 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.