kevinlin311tw / Caffe-DeepBinaryCode

Supervised Semantics-preserving Deep Hashing (TPAMI18)

Home Page:https://arxiv.org/abs/1507.00101v2

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

About the model used on SUN397 dataset

fanwenyuan opened this issue · comments

Excuse me, when I was trying to train my own model on Sun397 but failed. Did you use a pre-trained model with another dataset?

Thanks for your interest in this work. As I can recall, we didn't train the model from scratch. Training from scratch may need additional tricks, and it is not the major scope of this work.

Instead, we trained the model using pre-trained weights from ILSVRC12. This leads to good performance. In addition, we empirically found that training the model using pre-trained weights from Places dataset leads to higher accuracy. I think this is mainly because Places datasets consists of scene images, where should better fit to the image categories in SUN397.