Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

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

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

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

Models/DINOv2

DINOv2

Reported on 20 benchmarks across 5 tasks · 2 papers · 6 SOTA

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

Computer Vision18 results

Image MatchingonPF-PASCAL
PCK· 2025-05-23
95.8
SOTA
Semantic Correspondence: Unified Benchmarking and a Strong Baseline arXiv:2505.18060
Image MatchingonAP-10K
PCK· 2025-05-23
87.4
SOTA
Semantic Correspondence: Unified Benchmarking and a Strong Baseline arXiv:2505.18060
Semantic correspondenceonPF-PASCAL
PCK· 2025-05-23
95.8
SOTA
Semantic Correspondence: Unified Benchmarking and a Strong Baseline arXiv:2505.18060
Semantic correspondenceonAP-10K
PCK· 2025-05-23
87.4
SOTA
Semantic Correspondence: Unified Benchmarking and a Strong Baseline arXiv:2505.18060
Visual Place RecognitiononNardo-Air
Recall@1· 2023-04-14
73.24
best: 76.06 (AnyLoc-VLAD-DINOv2)
SOTA
DINOv2: Learning Robust Visual Features without Supervision arXiv:2304.07193
Visual Place RecognitiononVP-Air
Recall@1· 2023-04-14
45.23
best: 66.74 (AnyLoc-VLAD-DINOv2)
SOTA
DINOv2: Learning Robust Visual Features without Supervision arXiv:2304.07193
Image MatchingonSPair-71k
PCK· 2025-05-23
85.2
best: 85.6 (GeoAware-SC (Supervised, AP-10K P.T.))
Semantic Correspondence: Unified Benchmarking and a Strong Baseline arXiv:2505.18060
Semantic correspondenceonSPair-71k
PCK· 2025-05-23
85.2
best: 85.6 (GeoAware-SC (Supervised, AP-10K P.T.))
Semantic Correspondence: Unified Benchmarking and a Strong Baseline arXiv:2505.18060
Visual Place RecognitiononNardo-Air R
Recall@1· 2023-04-14
71.83
best: 94.37 (AnyLoc-VLAD-DINO)
DINOv2: Learning Robust Visual Features without Supervision arXiv:2304.07193
Visual Place RecognitiononOxford RobotCar Dataset
Recall@1· 2023-04-14
39.79
best: 98.95 (AnyLoc-VLAD-DINOv2)
DINOv2: Learning Robust Visual Features without Supervision arXiv:2304.07193
Visual Place RecognitiononMid-Atlantic Ridge
Recall@1· 2023-04-14
24.75
best: 34.65 (AnyLoc-VLAD-DINOv2)
DINOv2: Learning Robust Visual Features without Supervision arXiv:2304.07193
Visual Place RecognitiononSt Lucia
Recall@1· 2023-04-14
78.62
best: 100 (EffoVPR)
DINOv2: Learning Robust Visual Features without Supervision arXiv:2304.07193
Visual Place RecognitiononHawkins
Recall@1· 2023-04-14
27.97
best: 65.25 (AnyLoc-VLAD-DINOv2)
DINOv2: Learning Robust Visual Features without Supervision arXiv:2304.07193
Visual Place RecognitiononLaurel Caverns
Recall@1· 2023-04-14
40.18
best: 61.61 (AnyLoc-VLAD-DINOv2)
DINOv2: Learning Robust Visual Features without Supervision arXiv:2304.07193
Visual Place RecognitiononGardens Point
Recall@1· 2023-04-14
71.5
best: 95.5 (AnyLoc-VLAD-DINOv2)
DINOv2: Learning Robust Visual Features without Supervision arXiv:2304.07193
Visual Place RecognitiononPittsburgh-30k-test
Recall@1· 2023-04-14
78.32
best: 95.4 (Pair-VPR-p)
DINOv2: Learning Robust Visual Features without Supervision arXiv:2304.07193
Visual Place Recognitionon17 Places
Recall@1· 2023-04-14
61.82
best: 95.3 (SegVLAD-FineT (M))
DINOv2: Learning Robust Visual Features without Supervision arXiv:2304.07193
Visual Place RecognitiononBaidu Mall
Recall@1· 2023-04-14
49.21
best: 80.4 (SegVLAD-PreT (M))
DINOv2: Learning Robust Visual Features without Supervision arXiv:2304.07193

Medical1 result

Semantic SegmentationonFine-Grained Grass Segmentation Dataset
mIoU· 2023-04-14
47.57
best: 51.96 (D2LS)
DINOv2: Learning Robust Visual Features without Supervision arXiv:2304.07193

Audio1 result

10-shot image generationonFine-Grained Grass Segmentation Dataset
mIoU· 2023-04-14
47.57
best: 51.96 (D2LS)
DINOv2: Learning Robust Visual Features without Supervision arXiv:2304.07193