mlsanityData to 13 Oct 2026

The Cityscapes Dataset for Semantic Urban Scene Understanding

arXiv 1604.01685 ↗First posted 6 Apr 2016cs.CVcited by 4,435

Not on the map. Why?

Cited by 129 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Visual understanding of complex urban street scenes is an enabling factor for a wide range of applications. Object detection has benefited enormously from large-scale datasets, especially in the context of deep learning. For semantic urban scene understanding, however, no current dataset adequately captures the complexity of real-world urban scenes. To address this, we introduce Cityscapes, a benchmark suite and large-scale dataset to train and test approaches for pixel-level and instance-level semantic labeling. Cityscapes is comprised of a large, diverse set of stereo video sequences recorded in streets from 50 different cities. 5000 of these images have high quality pixel-level annotations; 20000 additional images have coarse annotations to enable methods that leverage large volumes of weakly-labeled data. Crucially, our effort exceeds previous attempts in terms of dataset size, annotation richness, scene variability, and complexity. Our accompanying empirical study provides an in-depth analysis of the dataset characteristics, as well as a performance evaluation of several state-of-the-art approaches based on our benchmark.

Key facts. Cited by 4,435 papers in the map (data through 13 Oct 2026). First posted on arXiv 6 Apr 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2019: 1; 2020: 0; 2021: 874; 2022: 822; 2023: 854; 2024: 792; 2025: 632; 2026: 460.

4,435 papers.

Sort:

By area:

  1. 2023Segment Anythingcited by 8,195
  2. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,857
  3. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,930
  4. 2024SAM 2: Segment Anything in Images and Videoscited by 2,820
  5. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,344
  6. 2021Vision Transformers for Dense Predictioncited by 1,795
  7. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,353
  8. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,150
  9. 2021Transformers in Vision: A Surveycited by 1,010
  10. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 991
  11. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  12. 2023Vision-Language Models for Vision Tasks: A Surveycited by 837
38 more
  1. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 764
  2. 2021Domain Generalization: A Surveycited by 760
  3. 2022Block-NeRF: Scalable Large Scene Neural View Synthesiscited by 721
  4. 2022Language-driven Semantic Segmentationcited by 715
  5. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 658
  6. 2021KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3Dcited by 571
  7. 2021Argmax Flows and Multinomial Diffusion: Learning Categorical Distributionscited by 570
  8. 2022Vision Transformer Adapter for Dense Predictionscited by 565
  9. 2022Continual Test-Time Domain Adaptationcited by 523
  10. 2021RepVGG: Making VGG-style ConvNets Great Againcited by 520
  11. 2022InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutionscited by 482
  12. 2022TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Drivingcited by 479
  13. 2021Semi-Supervised Semantic Segmentation with Cross Pseudo Supervisioncited by 462
  14. 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 389
  15. 2024UniDepth: Universal Monocular Metric Depth Estimationcited by 377
  16. 2021Multi-Modal Fusion Transformer for End-to-End Autonomous Drivingcited by 373
  17. 2023Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Modelscited by 372
  18. 2022Decomposing NeRF for Editing via Feature Field Distillationcited by 370
  19. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 359
  20. 2023Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Imagecited by 359
  21. 2022Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentationcited by 343
  22. 2021Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scanscited by 336
  23. 2022OneFormer: One Transformer to Rule Universal Image Segmentationcited by 327
  24. 2021Membership Inference Attacks on Machine Learning: A Surveycited by 320
  25. 2021Pre-Trained Models: Past, Present and Futurecited by 319
  26. 2021CMT: Convolutional Neural Networks Meet Vision Transformerscited by 310
  27. 2022MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolationcited by 308
  28. 2021DSEC: A Stereo Event Camera Dataset for Driving Scenarioscited by 301
  29. 2023GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interestcited by 300
  30. 2021DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentationcited by 299
  31. 2021HDMapNet: An Online HD Map Construction and Evaluation Frameworkcited by 281
  32. 2021SegDiff: Image Segmentation with Diffusion Probabilistic Modelscited by 280
  33. 2022DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detectioncited by 271
  34. 2021Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentationcited by 268
  35. 2021DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effortcited by 264
  36. 2022SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentationcited by 252
  37. 2021A Survey on Deep Semi-supervised Learningcited by 250
  38. 2021Adaptive Fourier Neural Operators: Efficient Token Mixers for Transformerscited by 243

50 most cited of 4,435 All 4,435 (JSON)