How to adapt when the dataset of the target domain is much smaller than source domain

corenel / pytorch-adda

A PyTorch implementation for Adversarial Discriminative Domain Adaptation

MIT License

474 stars 139 forks source link

How to adapt when the dataset of the target domain is much smaller than source domain #30

Open universe27king opened 10 months ago

universe27king commented 10 months ago

eg.source domain has more than 8000 samples while target domain has about 200 samples. ACC decreases after adaptation, Reduce the learning rate and adapt epochs seems to be ineffective