search

er-muyue / DeFRCN

MIT License
181 stars 43 forks source link

Difference Between ’Remove‘ and ’Randinit‘ #41

Open xiaohei1001 opened 2 years ago

xiaohei1001 commented 2 years ago
  1. I am experimenting on my custom dataset. When I initialize with the ’Remove‘ setting, I can reach 40 nAP, but when I initialize with the 'Randinit' setting, the nAP is close to 0. Why is this?
  2. I noticed that your code is different from TFA. The combine operation is not used in 'Remove', which is equivalent to randomly initializing the weights of the novel and base classes. Why do it？ Looking forward to your reply.
xiaohei1001 commented 2 years ago

I have solved question 1, can you please answer question 2? Thanks！ @er-muyue