</> Code with Papers by Syntology

Datasets › GTA5

GTA5 (Grand Theft Auto 5)

Introduced by Stephan R. Richter et al. in Playing for Data: Ground Truth from Computer Games1 Jan 2016 archive 2025-07-28

The GTA5 dataset contains 24966 synthetic images with pixel level semantic annotation. The images have been rendered using the open-world video game Grand Theft Auto 5 and are all from the car perspective in the streets of American-style virtual cities. There are 19 semantic classes which are compatible with the ones of Cityscapes dataset.

Source: Adversarial Learning and Self-Teaching Techniques for Domain Adaptation in Semantic Segmentation Image Source: Richter et al

HomepageBenchmarksPapers JSON

Benchmarks archive 2025-07-28

All 7 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Synthetic-to-Real Translation GTAV-to-Cityscapes Labels DCF mIoU 77.7 Transferring to Real-World Layouts: A Depth-aware... chen742/PiPa +1 73 Compare
Domain Adaptation GTA5 to Cityscapes HALO mIoU 77.8 Hyperbolic Active Learning for Semantic Segmentation... paolomandica/HALO 28 Compare
Image-to-Image Translation GTAV-to-Cityscapes Labels MIC mIoU 75.9 MIC: Masked Image Consistency for Context-Enhanced... lhoyer/mic 22 Compare
Unsupervised Domain Adaptation GTAV-to-Cityscapes Labels MIC mIoU 75.9 MIC: Masked Image Consistency for Context-Enhanced... lhoyer/mic 20 Compare
Semantic Segmentation GTAV-to-Cityscapes Labels MIC mIoU 75.9 MIC: Masked Image Consistency for Context-Enhanced... lhoyer/mic 12 Compare
Domain Adaptation GTA5+Synscapes to Cityscapes MSCL mIoU 59.0 Multi-Source Domain Adaptation with Collaborative... — 5 Compare
Source-Free Domain Adaptation GTA5 to Cityscapes HALO mIoU 73.3 Hyperbolic Active Learning for Semantic Segmentation... paolomandica/HALO 1 Compare

Papers archive 2025-07-28

30 shown of 82 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 412. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
Improve Cross-domain Mixed Sampling with Guidance Training for Adaptive Segmentation 1 1 22 Mar 2024 not harvested
Transferring to Real-World Layouts: A Depth-aware Framework for Scene Adaptation 2 2 21 Nov 2023 not harvested
Dual-level Interaction for Domain Adaptive Semantic Segmentation 1 1 16 Jul 2023 not harvested
Learning Content-enhanced Mask Transformer for Domain Generalized Urban-Scene Segmentation 1 2 1 Jul 2023 not harvested
Hyperbolic Active Learning for Semantic Segmentation under Domain Shift 1 2 19 Jun 2023 ran 3 of 8 samples (5 unverified)
FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding 1 2 4 Apr 2023 ran 4 of 4 samples (0 unverified; 4 pointer-only for licence)
Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic Segmentation 1 4 14 Feb 2023 not harvested
Iterative Loop Method Combining Active and Semi-Supervised Learning for Domain Adaptive Semantic Segmentation 1 1 31 Jan 2023 not harvested
MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation 1 5 2 Dec 2022 not harvested
ELDA: Using Edges to Have an Edge on Semantic Segmentation Based UDA 1 1 16 Nov 2022 not harvested
PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation 1 8 14 Nov 2022 not harvested
Deliberated Domain Bridging for Domain Adaptive Semantic Segmentation 1 3 16 Sep 2022 not harvested
A Novel Unsupervised Domain Adaption Method for Depth-Guided Semantic Segmentation Using Coarse-to-Fine Alignment 0 2 13 Sep 2022 not harvested
G2L: A Global to Local Alignment Method for Unsupervised Domain Adaptive Semantic Segmentation 0 5 7 Sep 2022 not harvested
CLUDA : Contrastive Learning in Unsupervised Domain Adaptation for Semantic Segmentation 1 3 27 Aug 2022 not harvested
Exploring High-quality Target Domain Information for Unsupervised Domain Adaptive Semantic Segmentation 1 4 12 Aug 2022 not harvested
Prototypical Contrast Adaptation for Domain Adaptive Semantic Segmentation 1 1 14 Jul 2022 ran 1 of 1 samples (0 unverified)
HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation 1 5 27 Apr 2022 not harvested
ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer 1 5 25 Apr 2022 not harvested
SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation 1 6 19 Apr 2022 ran 1 of 1 samples (0 unverified; 1 pointer-only for licence)
Bidirectional Self-Training with Multiple Anisotropic Prototypes for Domain Adaptive Semantic Segmentation 1 3 16 Apr 2022 not harvested
Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentation 1 2 18 Mar 2022 ran 1 of 4 samples (3 unverified; 4 pointer-only for licence)
Smoothing Matters: Momentum Transformer for Domain Adaptive Semantic Segmentation 1 5 15 Mar 2022 ran 2 of 8 samples (6 unverified; 2 pointer-only for licence)
Multiple Fusion Adaptation: A Strong Framework for Unsupervised Semantic Segmentation Adaptation 1 1 1 Dec 2021 not harvested
TridentAdapt: Learning Domain-invariance via Source-Target Confrontation and Self-induced Cross-domain Augmentation 1 1 30 Nov 2021 not harvested
DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation 3 5 29 Nov 2021 ran 6 of 6 samples (0 unverified; 6 pointer-only for licence)
SPCL: A New Framework for Domain Adaptive Semantic Segmentation via Semantic Prototype-based Contrastive Learning 1 1 24 Nov 2021 not harvested
Pixel-level Intra-domain Adaptation for Semantic Segmentation 0 1 17 Oct 2021 not harvested
Domain Adaptive Semantic Segmentation via Regional Contrastive Consistency Regularization 1 1 11 Oct 2021 not harvested
Unsupervised Domain Adaptation for Semantic Segmentation via Low-level Edge Information Transfer 0 1 18 Sep 2021 not harvested

The full list of 82 is in the JSON twin.

Dataset loaders archive 2025-07-28

milesial/Pytorch-UNetpytorch

1 loader as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

Semantic SegmentationDomain AdaptationImage-to-Image TranslationUnsupervised Domain AdaptationSource-Free Domain AdaptationSynthetic-to-Real TranslationOne-shot Unsupervised Domain Adaptation

License archive 2025-07-28

Research and educational use only

Modalities archive 2025-07-28

Images

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • GTA5
  • GTAV-to-Cityscapes Labels
  • GTA5 to Cityscapes
  • GTA5+Synscapes to Cityscapes

4 variant names, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections