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/DecoupleNet D2

DecoupleNet D2

Reported on 10 benchmarks across 8 tasks

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

Methodology4 results

  • 3DonDIOR-R
    mAP· uses extra data
    67.08
    best: 74.54 (MAE+MTP(ViT-L+RVSA))
  • 2D ClassificationonDIOR-R
    mAP· uses extra data
    67.08
    best: 74.54 (MAE+MTP(ViT-L+RVSA))
  • 2D Object DetectiononDIOR-R
    mAP· uses extra data
    67.08
    best: 74.54 (MAE+MTP(ViT-L+RVSA))
  • 16konDIOR-R
    mAP· uses extra data
    67.08
    best: 74.54 (MAE+MTP(ViT-L+RVSA))

Medical2 results

  • Semantic SegmentationonLoveDA
    Category mIoU
    53.1
    best: 56.16 (U-Net (MaxViT-S))
  • Semantic SegmentationonUAVid
    Mean IoU
    65.8
    best: 73.34 (U-Net Ensemble)

Computer Vision2 results

  • Object DetectiononDIOR-R
    mAP· uses extra data
    67.08
    best: 74.54 (MAE+MTP(ViT-L+RVSA))
  • Image ClassificationonRESISC45
    Top 1 Accuracy
    95.87
    best: 96.83 (ResNet50)

Audio2 results

  • 10-shot image generationonLoveDA
    Category mIoU
    53.1
    best: 56.16 (U-Net (MaxViT-S))
  • 10-shot image generationonUAVid
    Mean IoU
    65.8
    best: 73.34 (U-Net Ensemble)