-
Notifications
You must be signed in to change notification settings - Fork 196
Description
Hi PAIR-code/saliency team,
Thanks for your great work and contribution to the community! Your package helped a lot for my research.
I am just wondering if you would be interested in our new attribution method, which improves the quality of IG-based methods (e.g., IG, GIG, and BlurIG). The paper is accepted by and will be presented in CVPR 2023. Here is the link if you are interested: https://arxiv.org/abs/2303.14242
Since I heavily used your package during my research so I am happy to share/contribute our method if you are interested.
I have already read the contributing guidelines and submitted the CLA. Since the code I have is based on different IG-based methods, I am just wondering how can I start to contribute.
We are open to any suggestions, instructions, and discussion. Again, thanks for your package and the great work!