-
U have used Segmentation classes for creating Augmented images.Will the Augmented images be used for training?If so aren't we using fully supervised data for training? Please let me know
-
With 2 v100 / 16G, low performance
I use syncbn
-
Hi, Great work! It is very promising.
I have some problems about the training procedures and datasets:
(1) The training of co-peak module, and the testing of final instance co-segmentation share t…
-
We are using Segmentation classes of Pascal VOC to generate Augmented images which inturn is used totrain the model which means that we are using fully supervised data isn't it??So how is the model w…
-
hi,@GuoleiSun,I am confused that How to prepare the "pre-computed object proposals".
Hope to receive your reply!
-
Hello, very nice project !
I'm confused about the "--loss" hyperparameters, could you give some examples for such hyperparameter and what is it set in your experiment? could you provide examples for…
-
Hi,
we use the default parameters of PRM (https://github.com/ZhouYanzhao/PRM/blob/pytorch/demo/config.yml) to train the classification network, (change the train_splits from trainval to trianaug, o…
-
Dear Jiwoon, in the file 'train_irn.py', I noticed that GN was tuning using the inference data in the latest commit, [location](https://github.com/jiwoon-ahn/irn/blob/master/step/train_irn.py#L87). Is…
-
Hi,
Great work and very impressive results.
I have three problems related to the paper and hope you could help me solve this:
1. Based on your experience, how many images of a certain class are…
-
Hi,
This is a very insteresting work,
But we are confused about the 'datasets/proposal_dict.json' part.
We refer to MCG (https://www2.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/mcg/)…