search

chs20 / RobustVLM

[ICML 2024] Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models
MIT License
67 stars 3 forks source link

Adversarial Training FLARE4 #5

Closed hossainzarif closed 3 months ago

hossainzarif commented 3 months ago

Hello, while going through your repository, I noticed in your adversarial_training_clip.py you've only utilized the experiment_name argument for file saving purposes. However, when I attempted to run the file with other experiment_name (such as TECOA4), it ran the same functions as the (FLARE4). Does this repository include all the required modules and functions to execute the unsupervised adversarial training method (i.e., FLARE4)?

nmndeep commented 3 months ago

Hi, Thanks for your interest. In the readme, we provide the command to run for TeCoA. experiment_name is used for logging purposes. The difference between FARE and TeCoA is set implicitly by the inner_loss arg. As long as you run the command for TeCoA from the Readme - it should work. Hope this helps.