Khoi Pham

I'm also interested in using the dataset. Is there any information on when it would be available again?

Your implementation is exactly as equation 2. Then can you help me explain what does it mean by removing the positives from the denominator in supplementary section 11? Many thanks.

I agree we need to mask out the positive samples in the denominator, since that is the motivation of using labels for contrastive learning right? I also observe lower training...

Thank you for your answer. Can I ask some more questions about your experience finetuning Big-Lama with object-aware masks? 1. During the finetuning process, did you ever encounter some inpainting...

Thanks again. Just want to clarify one more thing since it was not explicitly stated in your answer. When generating object-aware mask to finetune LaMa, did you use masks from...

Can you point me to which line? I put them in order before saving, so they should be in consecutive order.