SIIM-ISIC Melanoma Classification 2020

2020 SIIM-ISIC Melanoma Classification
Competition link: https://www.kaggle.com/c/siim-isic-melanoma-classification

Transcript

1. SIIM-ISIC Melanoma Classification いのうえ
2. Overview → →
3. Last year’s solution (Link) ↓
4. My approach summary Region model EfficientNetB3 TPU models EfficientNets TPU models EfficientNets TPU models EfficientNets TPU models EfficientNets TPU models EfficientNets TPU models EfficientNets TPU models EfficientNets TPU models Effnets Crop-model RegNet16, 80 Crop model RegNet16, 80 Patch-Attention-model RegNets Patch-Attention-model RegNets Patch-Attention-model RegNets Patch Attention model Effnets, RegNets Ridge Stacking TPU models EfficientNets TPU models EfficientNets TPU models EfficientNets TPU models EfficientNets TPU models Effnets Ridge Stacking
5. Interesting Discussion (Link) ↓
6. Region model ↓
7. Patch-Based Attention model (link)
8. Postprocessing?
9. Postprocessing? 以上の予測値を 倍 →
10. Key discussion (link)
11. 1st place (link) 2018+2019+2020's data or 2020 only →
12. 2nd place (link) → EfficientNet-B6, 512x512, BS64, no metadata (CV 0.9336 / public 0.9534) EfficientNet-B7, 640x640, BS32, gradient accumulation 2, no metadata (CV 0.9389 / public 0.9525) Model 1, trained on combined training and pseudolabeled test data (CV 0.9438 / public 0.9493)
13. 2nd place (link) → EfficientNet-B6, 512x512, BS64, no metadata (CV 0.9336 / public 0.9534) EfficientNet-B7, 640x640, BS32, gradient accumulation 2, no metadata (CV 0.9389 / public 0.9525) Model 1, trained on combined training and pseudolabeled test data (CV 0.9438 / public 0.9493)
14. Others