CRST
CRST copied to clipboard
yzou2
Code for <Confidence Regularized Self-Training> in ICCV19 (Oral)
why we use p(k|x_t, w) / λ_k in the target domain instead of only p(k|x_t, w). In my opinion, λ_k is used for select confidence threshold as in Eq.4
https://github.com/yzou2/CRST/blob/f7e4df0f9310d3a1ce583602a6a2064c4d7a6483/deeplab/datasets.py#L584 If you use this method to read SYNTHIA ground truth label, the output will be wrong. And this should work `label = np.asarray(imageio.imread(datafiles["label"], format='PNG-FI'))[:,:,0]`
Hi, I ran the mrkld.sh script with the right data paths. I did not change anything else. The training process seems to have something wrong, The mIoU is going down...
Thanks for checking this issue. I attempts to install python2.7 + pytorch0.4.0 on my machines, BUT FAILED EVERYTIME ... Then I wonder: 1) what the difference in python3.6.9 + opencv...
I wanted to do the cross entropy loss of the source domain and the target domain respectively, and then sum them up，backword total loss. But nan always happens. What's the...
Hi, After reading the paper I was expecting a ResNet-38 based implementation as it yielded the better results than DeepLabV2 but if I am not mistaken there is only a...
Hi, I'm trying to get the Synthia transfer to work, and I cant see to do so. I followed the hyperparameter settings in #14 and using the source model in...
Hello！I successfully ran the first round, but encountered such a problem in the next round, what is the reason? Why can the first round succeed, but the following will not...
Hi, For implementation detail for Office-31 and Visda17, do you also follow those two steps? 1) Pretraining on the source dataset 2) Self-training on the target dataset If so, could...
