TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/DINO

DINO

Reported on 21 benchmarks across 9 tasks · 3 papers · 14 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision14 results

  • Object DetectiononVME & CDSI
    mAP50· 2025-05-28
    86.5
    SOTA
    VME: A Satellite Imagery Dataset and Benchmark for Detecting Vehicles in the Middle East and BeyondarXiv:2505.22353
  • Visual Place RecognitiononNardo-Air R
    Recall@1· 2021-04-29
    84.51
    best: 94.37 (AnyLoc-VLAD-DINO)
    SOTA
    Emerging Properties in Self-Supervised Vision TransformersarXiv:2104.14294
  • Visual Place RecognitiononNardo-Air
    Recall@1· 2021-04-29
    57.75
    best: 76.06 (AnyLoc-VLAD-DINOv2)
    SOTA
    Emerging Properties in Self-Supervised Vision TransformersarXiv:2104.14294
  • Visual Place RecognitiononMid-Atlantic Ridge
    Recall@1· 2021-04-29
    27.72
    best: 34.65 (AnyLoc-VLAD-DINOv2)
    SOTA
    Emerging Properties in Self-Supervised Vision TransformersarXiv:2104.14294
  • Visual Place RecognitiononHawkins
    Recall@1· 2021-04-29
    46.61
    best: 65.25 (AnyLoc-VLAD-DINOv2)
    SOTA
    Emerging Properties in Self-Supervised Vision TransformersarXiv:2104.14294
  • Visual Place RecognitiononLaurel Caverns
    Recall@1· 2021-04-29
    41.07
    best: 61.61 (AnyLoc-VLAD-DINOv2)
    SOTA
    Emerging Properties in Self-Supervised Vision TransformersarXiv:2104.14294
  • Visual Place RecognitiononGardens Point
    Recall@1· 2021-04-29
    78.5
    best: 95.5 (AnyLoc-VLAD-DINOv2)
    SOTA
    Emerging Properties in Self-Supervised Vision TransformersarXiv:2104.14294
  • Visual Place RecognitiononVP-Air
    Recall@1· 2021-04-29
    24.02
    best: 66.74 (AnyLoc-VLAD-DINOv2)
    SOTA
    Emerging Properties in Self-Supervised Vision TransformersarXiv:2104.14294
  • Visual Place Recognitionon17 Places
    Recall@1· 2021-04-29
    61.82
    best: 95.3 (SegVLAD-FineT (M))
    SOTA
    Emerging Properties in Self-Supervised Vision TransformersarXiv:2104.14294
  • Visual Place RecognitiononOxford RobotCar Dataset
    Recall@1· 2021-04-29
    15.71
    best: 98.95 (AnyLoc-VLAD-DINOv2)
    Emerging Properties in Self-Supervised Vision TransformersarXiv:2104.14294
  • Visual Place RecognitiononSt Lucia
    Recall@1· 2021-04-29
    45.22
    best: 100 (EffoVPR)
    Emerging Properties in Self-Supervised Vision TransformersarXiv:2104.14294
  • Visual Place RecognitiononPittsburgh-30k-test
    Recall@1· 2021-04-29
    70.13
    best: 95.4 (Pair-VPR-p)
    Emerging Properties in Self-Supervised Vision TransformersarXiv:2104.14294
  • Visual Place RecognitiononBaidu Mall
    Recall@1· 2021-04-29
    48.3
    best: 80.4 (SegVLAD-PreT (M))
    Emerging Properties in Self-Supervised Vision TransformersarXiv:2104.14294
  • Image ClassificationonOmniBenchmark
    Average Top-1 Accuracy· 2021-04-29
    38.9
    best: 47.6 (NOAH-ViTB/16)
    Emerging Properties in Self-Supervised Vision TransformersarXiv:2104.14294

Methodology7 results

  • 3DonVME & CDSI
    mAP50· 2025-05-28
    86.5
    SOTA
    VME: A Satellite Imagery Dataset and Benchmark for Detecting Vehicles in the Middle East and BeyondarXiv:2505.22353
  • 2D ClassificationonVME & CDSI
    mAP50· 2025-05-28
    86.5
    SOTA
    VME: A Satellite Imagery Dataset and Benchmark for Detecting Vehicles in the Middle East and BeyondarXiv:2505.22353
  • 2D Object DetectiononVME & CDSI
    mAP50· 2025-05-28
    86.5
    SOTA
    VME: A Satellite Imagery Dataset and Benchmark for Detecting Vehicles in the Middle East and BeyondarXiv:2505.22353
  • 16konVME & CDSI
    mAP50· 2025-05-28
    86.5
    SOTA
    VME: A Satellite Imagery Dataset and Benchmark for Detecting Vehicles in the Middle East and BeyondarXiv:2505.22353
  • ClassificationonBrain Tumor MRI Dataset
    F1 score· 2022-06-08
    0.9909
    SOTA
    CASS: Cross Architectural Self-Supervision for Medical Image AnalysisarXiv:2206.04170
  • Partial Label LearningonAutoimmune Dataset
    F1 score· 2022-06-08
    0.8445
    best: 0.8717 (CASS)
    CASS: Cross Architectural Self-Supervision for Medical Image AnalysisarXiv:2206.04170
  • ClassificationonAutoimmune Dataset
    F1 score· 2022-06-08
    0.8639
    best: 0.891 (Swin Transformer Base (Patch 4 Window 12))
    CASS: Cross Architectural Self-Supervision for Medical Image AnalysisarXiv:2206.04170