Brief Review — TernausNet: U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation
Winning Solution (1st out of 735) in Kaggle: Carvana Image Masking Challenge
TernausNet: U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation
TernausNet, by Lyft Inc., and Massachusetts Institute of Technology
2018 arXiv v1, Over 650 Citations (Sik-Ho Tsang @ Medium)
- Jaccard index (Intersection Over Union) is used as evaluation metric.
Validation learning curves in Fig. 3 show benefits of the pretraining approach.
- After 100 epochs, for validation subset:
- LeCun uniform initializer: IoU = 0.593
- The Encoder is pre-trained on ImageNet: IoU = 0.686
- Fully pre-trained U-Net on Carvana: IoU = 0.687
Pretrained models obtain better segmentation results.