Saul Zhang

Has anyone achieved the accuracy in the paper through the recurrence model?

5

Can the author publish a detailed data set partitioning method or publish a final prediction model?

A preblem in file rpnet/rpnet.py

2

line376: loss += 0.8 * nn.L1Loss().cuda()(fps_pred[:][:2], y[:][:2]) line377: loss += 0.2 * nn.L1Loss().cuda()(fps_pred[:][2:], y[:][2:]) In the file rpnet.py ,we can know that these two lines refers the L1Loss about the...

Question about constant terms C1, C2.

2

From the original paper, C1=(KL)², but I didn't see L=255 just K1 = 0.01 in the specific implementation of the code. Can the item L be discarded?Does the code mean...

Can we use the bounding box in the testing set?

3

Dear Ziwei Liu: A problem confuses me.Can we use the bounding box position as a konwn information in the testing set. I notice that you trian three network for upper,lower...

About the GFlops on the ADE20K dataset.

3

Hi, I can not find the reported GFlops on the paper about the model Vit-Adapter-L (Mask2former/Beit v2/crop size 896), can you tell me the relevant data or the method to...

Thank you for your valuable contributions and open-source code! Could you please provide the training configuration for re-implementing the segmentation task? Additionally, it would be wonderful if you could share...

Dear authors, Firstly, thanks for your great work. Recently, I've encountered an issue while utilizing the script detection/image_demo.py to perform inference using the instance segmentation model. In particular, I noticed...