search

xyutao / fscil

Official repository for Few-Shot Class-Incremental Learning (FSCIL)
221 stars 36 forks source link

About the result #13

Closed Ha0-W closed 4 years ago

Ha0-W commented 4 years ago

I wonder how to get the result of session > 2. We will train on the 25 images for some epochs. We evaluate the model after each epoch and choose the best result or just after the last epoch?

xyutao commented 4 years ago

Choose an intermediate model with a better performance trade-off between the old and new classes.

We've developed the acquisition-memory curves (in Fig.7 of supplementary material) to justify the selection of models, where a F score is computed to balance the accuracies of old and new classes. In this way, we can get a better recognition performance for longer sequence of learning.

You can access the CVPR website http://conferences.computer.org/cvpr, and download the supplementary material. username: cvpr20 passwd: conf20//

Ha0-W commented 4 years ago

Thanks!