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/NetVLAD (with GPM)

NetVLAD (with GPM)

Reported on 8 benchmarks across 1 task · 1 paper

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

Computer Vision8 results

  • Visual Place RecognitiononNordland
    Recall@1· 2023-02-28
    44.9
    best: 96.7 (QAA-DINOv2-B-8192)
    Global Proxy-based Hard Mining for Visual Place RecognitionarXiv:2302.14217
  • Visual Place RecognitiononNordland
    Recall@5· 2023-02-28
    50.2
    best: 98.6 (EffoVPR)
    Global Proxy-based Hard Mining for Visual Place RecognitionarXiv:2302.14217
  • Visual Place RecognitiononPittsburgh-250k-test
    Recall@1· uses extra data· 2023-02-28
    91.5
    best: 97 (FoL)
    Global Proxy-based Hard Mining for Visual Place RecognitionarXiv:2302.14217
  • Visual Place RecognitiononPittsburgh-250k-test
    Recall@10· uses extra data· 2023-02-28
    98.1
    best: 99.5 (BoQ)
    Global Proxy-based Hard Mining for Visual Place RecognitionarXiv:2302.14217
  • Visual Place RecognitiononPittsburgh-250k-test
    Recall@5· uses extra data· 2023-02-28
    97.2
    best: 99.5 (FoL)
    Global Proxy-based Hard Mining for Visual Place RecognitionarXiv:2302.14217
  • Visual Place RecognitiononMapillary val
    Recall@1· 2023-02-28
    82
    best: 97.6 (QAA-DINOv2-B-8192)
    Global Proxy-based Hard Mining for Visual Place RecognitionarXiv:2302.14217
  • Visual Place RecognitiononMapillary val
    Recall@10· 2023-02-28
    91.4
    best: 97.7 (Pair-VPR-p)
    Global Proxy-based Hard Mining for Visual Place RecognitionarXiv:2302.14217
  • Visual Place RecognitiononMapillary val
    Recall@5· 2023-02-28
    90.4
    best: 97.3 (Pair-VPR-p)
    Global Proxy-based Hard Mining for Visual Place RecognitionarXiv:2302.14217