Datasets › BDD100K

BDD100K

Introduced by Fisher Yu et al. in BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning8 Apr 2020 archive 2025-07-28

Datasets drive vision progress, yet existing driving datasets are impoverished in terms of visual content and supported tasks to study multitask learning for autonomous driving. Researchers are usually constrained to study a small set of problems on one dataset, while real-world computer vision applications require performing tasks of various complexities. We construct BDD100K, the largest driving video dataset with 100K videos and 10 tasks to evaluate the exciting progress of image recognition algorithms on autonomous driving. The dataset possesses geographic, environmental, and weather diversity, which is useful for training models that are less likely to be surprised by new conditions. Based on this diverse dataset, we build a benchmark for heterogeneous multitask learning and study how to solve the tasks together. Our experiments show that special training strategies are needed for existing models to perform such heterogeneous tasks. BDD100K opens the door for future studies in this important venue. More detail is at the dataset home page.

Benchmarks archive 2025-07-28

All 16 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.

Syntology 3 newer papers were judged to report on this dataset's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): Semantic Segmentation · BDD100K val (1 judged, 0 placed), Multiple Object Tracking · BDD100K val (1 judged, 0 placed), 2D Object Detection · BDD100K val (1 judged, 0 placed), Multi-Object Tracking · BDD100K (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

First row (archive order)PaperCode
Semantic Segmentation BDD100K val VLTSeg mIoU 72.5 Strong but simple: A Baseline for Domain Generalized... VLTSeg/VLTSeg 24 Compare
Lane Detection BDD100K val TwinLiteNetPlus-Large IoU (%) 34.2 TwinLiteNetPlus: A Stronger Model for Real-time Drivable... chequanghuy/TwinLiteNet +1 11 Compare
Drivable Area Detection BDD100K val YOLOPv2 mIoU 93.2 YOLOPv2: Better, Faster, Stronger for Panoptic Driving Perception PINTO0309/PINTO_model_zoo +1 10 Compare
Multiple Object Tracking BDD100K val ByteTrack mMOTA 45.5 ByteTrack: Multi-Object Tracking by Associating Every... PaddlePaddle/PaddleDetection +9 9 Compare
Multi-Object Tracking and Segmentation BDD100K val UNINEXT-H mMOTSA 35.7 Universal Instance Perception as Object Discovery and Retrieval MasterBin-IIAU/UNINEXT 8 Compare
Video Instance Segmentation BDD100K val PCAN mMOTSA 27.4 Prototypical Cross-Attention Networks for Multiple... SysCV/pcan 6 Compare
Multiple Object Tracking BDD100K test ContrasTR mMOTA 42.8 Contrastive Learning for Multi-Object Tracking with Transformers pfdp0/ContrasTR 5 Compare
Instance Segmentation BDD100K val Mask Transfiner AP 23.6 Mask Transfiner for High-Quality Instance Segmentation SysCV/transfiner 4 Compare
Unsupervised Panoptic Segmentation BDD100K val CUPS (40 pseudo-classes) PQ 21.9 Scene-Centric Unsupervised Panoptic Segmentation visinf/cups 4 Compare
2D Object Detection BDD100K val InternImage-H mAP 38.8 InternImage: Exploring Large-Scale Vision Foundation... opengvlab/internimage +2 1 Compare
Amodal Panoptic Segmentation BDD100K val APSNet AP 29.2 Amodal Panoptic Segmentation — 1 Compare
Multi-Object Tracking BDD100K CO-MOT TETA 52.8 Bridging the Gap Between End-to-end and Non-End-to-end... bingfengyan/visam +1 1 Compare
Multiple Object Track and Segmentation BDD100K val PCAN mMOTSA 27.4 Prototypical Cross-Attention Networks for Multiple... SysCV/pcan 1 Compare
Object Detection BDD100K CDDMSL MAP 27.1 Semi-Supervised Domain Generalization for Object... sinamalakouti/CDDMSL 1 Compare
Object Detection BDD100K val hybrid incremental net mAP@0.5 45.7 On Generalizing Detection Models for Unconstrained Environments prajjwal1/autonomous-object-detection 1 Compare
Steering Control BDD100K val FM-Net Accuracy 85.03 Learning to Steer by Mimicking Features from... cardwing/Codes-for-Steering-Control +1 1 Compare

Papers archive 2025-07-28

papers with a benchmark row: 49 · with a code link: 47 · where Syntology ran a sample: 23 (21 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument) Syntology

Show: all papers with a benchmark rowonly where code ran (23 of 49 with a benchmark row: 21 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 49 of 49 with a leaderboard row on this dataset's benchmarks, newest first by the archive's date (ties by slug; undated papers last).

The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset, not that list; the archive's count for this dataset is 469. The Syntology column is from Syntology's graph, stated per sample; it is not part of any archive number. A line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified” (C is a part of N, never taken away from it); the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. When the archive marks a repository official for the paper, the cell starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

PaperCodeResultsDateSamples run Syntology
Scene-Centric Unsupervised Panoptic Segmentation 1 3 2 Apr 2025 official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified
TriLiteNet: Lightweight Model for Multi-Task Visual Perception 1 2 17 Mar 2025 not harvested
DSNet: A Novel Way to Use Atrous Convolutions in Semantic Segmentation 1 2 6 Jun 2024 not harvested
TwinLiteNetPlus: A Stronger Model for Real-time Drivable Area and Lane Segmentation 2 8 25 Mar 2024 not harvested
SERNet-Former: Semantic Segmentation by Efficient Residual Network with Attention-Boosting Gates and Attention-Fusion Networks 2 1 28 Jan 2024 not harvested
Unsupervised Universal Image Segmentation 2 1 28 Dec 2023 official (archive's flag): 6 ran · 13 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 9 where Syntology's instrument failed) · 2 unverified (1 pointer-only for licence)
Strong but simple: A Baseline for Domain Generalized Dense Perception by CLIP-based Transfer Learning 1 1 4 Dec 2023 not harvested
MRFP: Learning Generalizable Semantic Segmentation from Sim-2-Real with Multi-Resolution Feature Perturbation 1 2 30 Nov 2023 not harvested
Contrastive Learning for Multi-Object Tracking with Transformers 1 2 14 Nov 2023 not harvested
You Only Look at Once for Real-time and Generic Multi-Task 1 2 2 Oct 2023 not harvested
Semi-Supervised Domain Generalization for Object Detection via Language-Guided Feature Alignment 1 1 24 Sep 2023 not harvested
TwinLiteNet: An Efficient and Lightweight Model for Driveable Area and Lane Segmentation in Self-Driving Cars 1 2 20 Jul 2023 not harvested
Bridging the Gap Between End-to-end and Non-End-to-end Multi-Object Tracking 2 1 22 May 2023 not harvested
Universal Instance Perception as Object Discovery and Retrieval 1 2 12 Mar 2023 official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (2 pointer-only for licence)
Unifying Short and Long-Term Tracking with Graph Hierarchies 1 1 6 Dec 2022 official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified
MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors 4 1 17 Nov 2022 not harvested
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions 3 1 10 Nov 2022 official: harvested, nothing ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified
QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Tracking 2 2 12 Oct 2022 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified
YOLOPv2: Better, Faster, Stronger for Panoptic Driving Perception 2 2 24 Aug 2022 not harvested
Tackling multiple object tracking with complicated motions—Re-designing the integration of motion and appearance 0 1 22 Aug 2022 not harvested
Tracking Every Thing in the Wild 1 1 26 Jul 2022 not harvested
Towards Grand Unification of Object Tracking 1 2 14 Jul 2022 official (archive's flag): 5 ran · 6 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 1 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (1 pointer-only for licence)
SFNet: Faster, Accurate, and Domain Agnostic Semantic Segmentation via Semantic Flow 1 2 10 Jul 2022 not harvested
HybridNets: End-to-End Perception Network 3 2 17 Mar 2022 not harvested
Amodal Panoptic Segmentation 0 1 23 Feb 2022 not harvested
Mask Transfiner for High-Quality Instance Segmentation 1 1 26 Nov 2021 official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified
ByteTrack: Multi-Object Tracking by Associating Every Detection Box 10 2 13 Oct 2021 official (archive's flag): 4 ran · 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (1 pointer-only for licence)
YOLOP: You Only Look Once for Panoptic Driving Perception 5 2 25 Aug 2021 official (archive's flag): 5 ran · 13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified (2 pointer-only for licence)
Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation 1 13 22 Jun 2021 official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified
Fast and Accurate Scene Parsing via Bi-direction Alignment Networks 1 1 25 May 2021 not harvested
Rethinking BiSeNet For Real-time Semantic Segmentation 6 2 27 Apr 2021 official (archive's flag): 2 ran · 9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified (1 pointer-only for licence)
Quasi-Dense Similarity Learning for Multiple Object Tracking 3 1 11 Jun 2020 not harvested
Semantic Flow for Fast and Accurate Scene Parsing 6 3 24 Feb 2020 official (archive's flag): 2 ran · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified (1 pointer-only for licence)
On Generalizing Detection Models for Unconstrained Environments 1 1 28 Sep 2019 not harvested
Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation 11 1 24 Sep 2019 official (archive's flag): 1 ran · 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified (1 pointer-only for licence)
What's There in the Dark 1 1 24 Sep 2019 not harvested
Deep High-Resolution Representation Learning for Visual Recognition 42 1 20 Aug 2019 21 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 1 violated, 15 with no contract checked; 5 where Syntology's instrument failed) · 13 unverified (21 pointer-only for licence)
Learning Lightweight Lane Detection CNNs by Self Attention Distillation 2 1 2 Aug 2019 official (archive's flag): 1 ran · 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (1 pointer-only for licence)
Expectation-Maximization Attention Networks for Semantic Segmentation 5 1 31 Jul 2019 not harvested
Cascade R-CNN: High Quality Object Detection and Instance Segmentation 4 1 24 Jun 2019 not harvested
Partial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture Search 2 2 9 Mar 2019 not harvested
Learning to Steer by Mimicking Features from Heterogeneous Auxiliary Networks 2 1 7 Nov 2018 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified
Dual Attention Network for Scene Segmentation 12 1 9 Sep 2018 official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (5 pointer-only for licence)
BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation 21 1 2 Aug 2018 14 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified (3 pointer-only for licence)
BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning 4 1 12 May 2018 official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation 78 1 7 Feb 2018 community repositories only · 44 ran (of which 17 constructed an object rather than computing a result; 28 with no instrument failure: 2 honoured, 0 violated, 26 with no contract checked; 16 where Syntology's instrument failed) · 28 unverified (40 pointer-only for licence)
ICNet for Real-Time Semantic Segmentation on High-Resolution Images 18 1 27 Apr 2017 not harvested
Mask R-CNN 179 1 20 Mar 2017 101 ran (of which 3 constructed an object rather than computing a result; 77 with no instrument failure: 2 honoured, 1 violated, 74 with no contract checked; 24 where Syntology's instrument failed) · 39 unverified (32 pointer-only for licence)
Pyramid Scene Parsing Network 67 1 4 Dec 2016 community repositories only · 21 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 7 where Syntology's instrument failed) · 8 unverified (5 pointer-only for licence)

Dataset loaders archive 2025-07-28

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

Tasks archive 2025-07-28

License archive 2025-07-28

Mixed License

Modalities archive 2025-07-28

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • BDD100K
  • BDD100K val
  • BDD100K test
  • BDD100K-APS

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