DINO-MC

Reported on 4 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Computer Vision4 results

Multi-Label Image ClassificationonBigEarthNet-10%
mean average precision· uses extra data· 2023-03-12
84.2
SOTA
Extending global-local view alignment for self-supervised learning with remote sensing imagery arXiv:2303.06670
Image ClassificationonBigEarthNet-10%
mean average precision· uses extra data· 2023-03-12
84.2
SOTA
Extending global-local view alignment for self-supervised learning with remote sensing imagery arXiv:2303.06670
Multi-Label Image ClassificationonBigEarthNet
mAP (micro)· uses extra data· 2023-03-12
88.75
best: 91.8 (MoCo-v2 (ResNet50, fine tune))
Extending global-local view alignment for self-supervised learning with remote sensing imagery arXiv:2303.06670
Image ClassificationonBigEarthNet
mAP (micro)· uses extra data· 2023-03-12
88.75
best: 91.8 (MoCo-v2 (ResNet50, fine tune))
Extending global-local view alignment for self-supervised learning with remote sensing imagery arXiv:2303.06670