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/ILLUME

ILLUME

Reported on 10 benchmarks across 4 tasks · 1 paper

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

Methodology4 results

  • Domain AdaptationonCityscapes to Foggy Cityscapes
    mAP@0.5
    43.8
    best: 66.8 (ALDI++(Resnet50+FPN))
  • Domain AdaptationonBDD100k to Cityscapes
    mAP
    29.6
    best: 46.5 (RT-DATR(real-time, 640x640，R-34))
  • Domain AdaptationonSIM10K to Cityscapes
    mAP@0.5
    53.1
    best: 77.8 (ALDI++)
  • Domain AdaptationonPascal VOC to Clipart1K
    mAP
    41.6
    best: 55.6 (DDT)

Other4 results

  • Unsupervised Domain AdaptationonCityscapes to Foggy Cityscapes
    mAP@0.5
    43.8
    best: 66.8 (ALDI++(Resnet50+FPN))
  • Unsupervised Domain AdaptationonBDD100k to Cityscapes
    mAP
    29.6
    best: 46.5 (RT-DATR(real-time, 640x640，R-34))
  • Unsupervised Domain AdaptationonSIM10K to Cityscapes
    mAP@0.5
    53.1
    best: 77.8 (ALDI++)
  • Unsupervised Domain AdaptationonPascal VOC to Clipart1K
    mAP
    41.6
    best: 55.6 (DDT)

Natural Language Processing2 results

  • Visual Question Answering (VQA)onMM-Vet
    GPT-4 score· 2024-12-09
    37
    best: 74.24 (MMCTAgent (GPT-4 + GPT-4V))
    ILLUME: Illuminating Your LLMs to See, Draw, and Self-EnhancearXiv:2412.06673
  • Visual Question AnsweringonMM-Vet
    GPT-4 score· 2024-12-09
    37
    best: 74.24 (MMCTAgent (GPT-4 + GPT-4V))
    ILLUME: Illuminating Your LLMs to See, Draw, and Self-EnhancearXiv:2412.06673