ML Research Wiki / Benchmarks / Out-of-Distribution Detection / STL-10

STL-10

Out-of-Distribution Detection Benchmark

Performance Over Time

📊 Showing 6 results | 📏 Metric: Percentage correct

Top Performing Models

Rank Model Paper Percentage correct Date Code
1 Mixup (Gaussian) On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks 95.93 2019-05-27 📦 paganpasta/onmixup 📦 MacroMayhem/OnMixup
2 Mixup (Imagenet) On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks 83.28 2019-05-27 📦 paganpasta/onmixup 📦 MacroMayhem/OnMixup
3 Baseline (Imagenet) On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks 80.57 2019-05-27 📦 paganpasta/onmixup 📦 MacroMayhem/OnMixup
4 Dropout(Imagenet) On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks 78.93 2019-05-27 📦 paganpasta/onmixup 📦 MacroMayhem/OnMixup
5 Baseline (Gaussian) On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks 73.28 2019-05-27 📦 paganpasta/onmixup 📦 MacroMayhem/OnMixup
6 Dropout(Gaussian) On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks 70.57 2019-05-27 📦 paganpasta/onmixup 📦 MacroMayhem/OnMixup

All Papers (6)

paganpasta/onmixup MacroMayhem/OnMixup
paganpasta/onmixup MacroMayhem/OnMixup
paganpasta/onmixup MacroMayhem/OnMixup
paganpasta/onmixup MacroMayhem/OnMixup
paganpasta/onmixup MacroMayhem/OnMixup
paganpasta/onmixup MacroMayhem/OnMixup