FixSENet-154

Reported on 3 benchmarks across 2 tasks · 1 paper · 1 SOTA

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

Computer Vision3 results

Image ClassificationoniNaturalist
Top 1 Accuracy· uses extra data· 2019-06-14
75.4
best: 85.9 (AIMv2-3B (448 res))
SOTA
Fixing the train-test resolution discrepancy arXiv:1906.06423
Image ClassificationonCUB-200-2011
Accuracy· 2019-06-14
88.7
best: 92.8 (PIM)
Fixing the train-test resolution discrepancy arXiv:1906.06423
Fine-Grained Image ClassificationonCUB-200-2011
Accuracy· 2019-06-14
88.7
best: 92.8 (PIM)
Fixing the train-test resolution discrepancy arXiv:1906.06423