-
## 🚀 Feature
[This](https://arxiv.org/abs/2002.09518) papers proposes a new graph convolution/coarsening algorithm. The convolution layer doesn't use any kind of gnn, i.e it doesn't explicitly use th…
wsad1 updated
2 years ago
-
Hi, I noticed that the ground truth segmentation in YCBInEOAT dataset seems not good. The segmentation tracking by VOS is even worse. For example, if we look at "bleach0", the object is partially segm…
-
### 🚀 The feature, motivation and pitch
[Masked Label Propagation](https://arxiv.org/abs/2009.03509)/Label Re-Use is a popular approach (especially on [OGB datasets](https://ogb.stanford.edu/docs/l…
-
首先和感谢您的工作以及代码的开源，帮助学习到了很多，但是对论文中的transductive FSL 的描述很迷惑，还望帮忙解决下：
论文附录里关于transductive的描述如下：
When classifying test instance xtest in the transdutive scenario, other test instances Xtest from the N ca…
-
Running `python transductive-vos.pytorch/run_video.py --img_dir [THE PATH TO COLOR FILES] --init_mask_file [THE INITIAL MASK FILE YOU PREPARED ABOVE] --mask_save_dir [WHERE TO SAVE]` to generate masks…
-
Hi, I downloaded models of transduction-vos according to README instructions. There are three checkpoints in the folder ```transductive-vos.pytorch```: ```davis_train.pth.tar```, ```davis_trainval.pth…
-
I tried to increase the performance of the Graph2Vec model by using increasing the worker parameter when initializing the model. But it seems that still, the model takes only 1 core to process the fit…
-
Thank you for your excellent work.
I also suffer performance degradation caused by class imbalance when implementing some classic work. At that time, I didn't think of any other methods except to s…
-
https://www-cs-faculty.stanford.edu/people/jure/pubs/graphsage-nips17.pdf
GraphSAGE
-
In the n-way k-shot( k>1) setting, the attended features of the support set are computed by summing k attended features, which are influenced by the query set. I wonder whether it is an inductive or t…