search

akshitac8 / tfvaegan

[ECCV 2020] Official Pytorch implementation for "Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification". SOTA results for ZSL and GZSL
MIT License
129 stars 32 forks source link

Question regarding fine-tuned features #30

Closed RitiP closed 2 years ago

RitiP commented 2 years ago

Hi @akshitac8 ,

I wanted to clarify the procedure of retrieving the finetuned features. The features provided in the datasets are ResNet101 features trained on ImageNet. How do you achieve the finetuned features that you have mentioned in the paper? The performance for fine-tuned features is superb!

akshitac8 commented 2 years ago

Hello @RitiP Thank you for your interest in our work. We follow the same procedure for finetuned features as mentioned in the f-vaegan-d2 paper.