jfzhuang / ifr Goto Github PK

Hi, the image path in 'CamVid/splits/test_image.txt' is not exists in the "CamVid 701_StillsRaw_full Dataset"(http://web4.cs.ucl.ac.uk/staff/g.brostow/MotionSegRecData/).Could you help me find out what is wrong?

Thanks for your wonderful work. From Table 1, I think it shows that the CAC or CPS method using the remaining unlabeled frames for training has a significant performance improvement compared to not using them. From 66.00 to 69.70, from 70.32 to 74.39. However, the paper says "no obvious improvement is gained.". Could you please explain that?

Some VSS methods aggregate features of neighborhood unlabeled frames to segment the current frame, so I think these methods also use unlabeled frames for training and they can be considered semi-supervised. Did I misunderstand something here?

Here is another problem I'm confusing.
The task of video semantic segmentation is to segment each frame of videos. But only several frames are labeled in the test set, the test performance in experiments is on several images rather than whole videos. I think it can not represent the performance of video semantic segmentation methods. Did I misunderstand something here?

Hi,

Thanks for your excellent work SSVS! I wonder if is it possible to provide the pretrained model on Cityscapes dataset?

Thank you so much!

Best,
Daisy