search

ZF4444 / MMAL-Net

This is a PyTorch implementation of the paper "Multi-branch and Multi-scale Attention Learning for Fine-Grained Visual Categorization (MMAL-Net)" (Fan Zhang, Meng Li, Guisheng Zhai, Yizhao Liu).
250 stars 57 forks source link

About the Loss func #19

Open xtzd opened 3 years ago

xtzd commented 3 years ago

Hi, I would like to discuss the loss func issue with you :) . Do you think using triplet loss or center loss instead of CE loss in FGVC category could increase the model performance? Thanks~

ZF4444 commented 3 years ago

Hi! Interesting idea, but I haven't tried it, so I don't have a definitive answer. These loss functions have been around for a long time, but In the fine-grained classification papers I've looked at, I don't see the use of these two loss functions for fine-grained classification.

haoweiz23 commented 3 years ago

I have tried these metric learning loss on fine-grained task. However, not work.