SemiSeg-Contrastive

SemiSeg-Contrastive copied to clipboard

About the feature vectors from teacher and student

1

Dear author, I am confused about the feature vectors used in contrastive learning. The teacher's feature vectors are simply obtained using the projection head g. Why use the projection head...

ccccly

Question about the contrastive loss

1

1. I am wondering why the memory are normalized for the input of selector, but the features are not. https://github.com/Shathe/SemiSeg-Contrastive/blob/dc53c6da64f91c1ebce320f6e2ce3cc9f3df7414/contrastive_losses.py#L36-L37 https://github.com/Shathe/SemiSeg-Contrastive/blob/dc53c6da64f91c1ebce320f6e2ce3cc9f3df7414/contrastive_losses.py#L47-L48 2. I am very confused why permute is needed...

lliuz

why my mean iou and iou for each class are all nan

1

748572179

Hi there, Thanks for the work! I trained this SSL model for semi-supervised domain adaptation semantic segmentation. I used the label ratio of 1/30, trained on the GTA5 dataset as...

suikei-wang

hello,think you for sharing your code.it is a very good job.can you give me the code of infer a picture ,think you vety much again

fengchecheyzy

Hi, Thanks for the interesting work. I have some questions about the paper (https://openaccess.thecvf.com/content/ICCV2021/papers/Alonso_Semi-Supervised_Semantic_Segmentation_With_Pixel-Level_Contrastive_Learning_From_a_Class-Wise_ICCV_2021_paper.pdf) 1. I do not find any explaination about the S_{c, \theta} of Eq.(8) in Section 4.2...

HeimingX

Time question

1

Hello! Thank you for your code implementation. As mentioned in the paper, all experiments were performed on a single NVIDIA Tesla V100 GPU, it would be very helpful if you...

mradul2