Ianresearch

Results 6 comments of Ianresearch

The wrong segmentation result in ''High Quality Segmentation..."

The image is something like this: https://small.justeasy.cn/wx/201801/9efb7f2097162a3595ce651a391d35ea.png https://small.justeasy.cn/wx/201801/a4eb4e980da27692d1783af7b033285a.png The whole wall is easy be segmented as sky, even the wall is far away form the sky in picture. What is...

Questation about the multi-class for the "High Quality Segmentation for Ultra High-resolution Images"

Thank you for reply. And I have another queatation.'The perturbed masks are randomly perturbed on ground truth with a random IoU threshold between 0.8 and 1.0' -- can you explain...

Questation about the multi-class for the "High Quality Segmentation for Ultra High-resolution Images"

OK. Thank you very much!

the code question in semantic_seg

Thanky you for reply. If I use the method in semantic segmentation, and the input image size is (512,512), the parameter shape should be the shape(1, num_classes, 512, 512) or...

the code question in semantic_seg

Hi tonysy, I use this paper method in my u-net semantic segmentation, but the result is not improved. Is there something wrong in my implementation process? The u-net reuslt is...

the code question in semantic_seg

I will try again.The dataset is long-tail distribution, the biggest class ration is 74% and The smallest proportion is only 0.2%.(74%,11%,14.8%,0.2%). Thank you very much.