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/CosPlace (ResNet-101 2048-D)

CosPlace (ResNet-101 2048-D)

Reported on 7 benchmarks across 1 task · 1 paper · 6 SOTA

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

Computer Vision7 results

  • Visual Place RecognitiononPittsburgh-30k-test
    Recall@5· 2022-04-05
    95.7
    best: 98.3 (ProGEO)
    SOTA
    Rethinking Visual Geo-localization for Large-Scale ApplicationsarXiv:2204.02287
  • Visual Place RecognitiononTokyo247
    Recall@10· uses extra data· 2022-04-05
    96.5
    best: 100 (Pair-VPR-p)
    SOTA
    Rethinking Visual Geo-localization for Large-Scale ApplicationsarXiv:2204.02287
  • Visual Place RecognitiononTokyo247
    Recall@5· uses extra data· 2022-04-05
    95.9
    best: 100 (Pair-VPR-p)
    SOTA
    Rethinking Visual Geo-localization for Large-Scale ApplicationsarXiv:2204.02287
  • Visual Place RecognitiononMapillary val
    Recall@1· 2022-04-05
    86.7
    best: 97.6 (QAA-DINOv2-B-8192)
    SOTA
    Rethinking Visual Geo-localization for Large-Scale ApplicationsarXiv:2204.02287
  • Visual Place RecognitiononMapillary val
    Recall@10· 2022-04-05
    93.4
    best: 97.7 (Pair-VPR-p)
    SOTA
    Rethinking Visual Geo-localization for Large-Scale ApplicationsarXiv:2204.02287
  • Visual Place RecognitiononMapillary val
    Recall@5· 2022-04-05
    92.1
    best: 97.3 (Pair-VPR-p)
    SOTA
    Rethinking Visual Geo-localization for Large-Scale ApplicationsarXiv:2204.02287
  • Visual Place RecognitiononPittsburgh-30k-test
    Recall@1· 2022-04-05
    90.4
    best: 95.4 (Pair-VPR-p)
    Rethinking Visual Geo-localization for Large-Scale ApplicationsarXiv:2204.02287