Gyungin

Thanks a lot for your reply - it'd be really great if I could get your script to convert VOC masks to a COCO format to ensure a fair comparison,...

Hi @xs1317 and thank you for your kind words and interest in our work. I'm having difficulties understanding your question as it seems you got the same results as the...

Sorry, I was too quick to reply to you earlier - I noticed that the numbers you compared to are the ones in the revised version rather than the arXiv...

Thank you very much for letting me know - I could confirm that the embedding file produces the numbers you got. To double check the code, I re-implemented to compute...

I've encountered the same error. I think by this time you perhaps have figured it out, but as a future reference for other people who run into the same issue:...

Hi @qdd1234, thank you very much for your interest in our work and sorry for the late reply. We are working on providing a demo (probably with 27 mid-level categories...

Hi both, Thank you for your input. First, to clarify a couple of points raised by @hq-deng's comment: 1. The DenseCLIP model we use is not trained with pixel-level labels....

Dear @baron0830 Apologies for the late reply and thanks for your interest in our work. Yes, they are necessary and you can download here: For MoCov2: https://dl.fbaipublicfiles.com/moco/moco_checkpoints/moco_v2_800ep/moco_v2_800ep_pretrain.pth.tar For SwAV: https://dl.fbaipublicfiles.com/deepcluster/swav_800ep_pretrain.pth.tar...

Dear @LLL-YUE, Many thanks for your interests in our work. What browsers are you currently using to download them? I've just reconfirmed that it's downloadable with Safari and Chrome (in...

Dear @Taoww21480, Thank you for your interests in our work and sorry for the late response. Please try the following links (due to the size of files, I can't attach...