Empirical Experiments
- Dataset:
- DRIVE,
- STARE,
- HRF,
- 2D Neurons
Quantitative result
Table 1: Quantitative results of segmentation performance of a baseline segmentation method on the same DRIVE (or STARE, HRF, NeuB1) test set while training on a different training set. Results are evaluated by average F1-score (%).
Visual Results
Exemplar DRIVE phantoms generated by Fila-GAN
Exemplar STARE phantoms generated by Fila-GAN
Exemplar HRF phantoms generated by Fila-GAN
Exemplar 2D Neuron phantoms generated by Fila-GAN
Exemplar DRIVE phantoms generated by Fila-sGAN