suyukun666 / ufo Goto Github PK

Hi~
Could you share the Pascal voc Dataset you used in experiment?
Thank you!
Best wishes

您好，非常想学习这篇代码，由于自身硬件设备限制无法完成训练，可否分享一下训练好的权重文件？

Can you please explain how to train/refine with new 2D RGB data? Do I need to convert the train data to COCO format?

作者您好，最近我尝试了下UFO模型，并且训练了Co-Segmentation和Video Salient Object Detection任务。但在测试过程中，有些令我比较疑惑的问题，特地来问下。

1. 采用原始模型权重进行测试的结果与我重新训练模型的测试结果不一致。

   • Co-Segmentation任务
     原始模型权重的测试结果
     
     重新训练模型的测试结果
     

   • Video Salient Object Detection任务
     原始模型权重的测试结果
     
     重新训练模型的测试结果
     
     两者间相差是比较大的，重新训练的模型均采用仓库中的配置，未作任何改动。目前，我还不清楚是什么原因。

Hi author, I would like to do further research based on your work, but I have some doubts that I hope you can answer for me. You mentioned in your paper that your model is unsupervised for the VSOD task, but I see that the code uses groundtruth for supervision, what is the reason for this?

Hi, would you be interested in adding UFO to Hugging Face Hub? The Hub offers free hosting, and it would make your work more accessible and visible to the rest of the ML community. We can setup an organization or a user account under which UFO can be added similar to github.

Example from other organizations:
Keras: https://huggingface.co/keras-io
Microsoft: https://huggingface.co/microsoft
Facebook: https://huggingface.co/facebook

Example spaces with repos:
github: https://github.com/salesforce/BLIP
Spaces: https://huggingface.co/spaces/akhaliq/BLIP

github: https://github.com/facebookresearch/omnivore
Spaces: https://huggingface.co/spaces/akhaliq/omnivore

and here are guides for adding spaces/models/datasets to your org

How to add a Space: https://huggingface.co/blog/gradio-spaces
how to add models: https://huggingface.co/docs/hub/adding-a-model
uploading a dataset: https://huggingface.co/docs/datasets/upload_dataset.html

Please let us know if you would be interested and if you have any questions, we can also help with the technical implementation.

I observed that several ground truth segmentation masks provided in the COCO-SEG for certain categories are noisy i.e. the masks are several other objects are also present along with the mask of the desired object. Some examples are cup, tennis racket (humans are segmented along with the racket in the ground truth mask). How should we deal with this? Do you pre-preprocess this dataset somehow? Thanks.

Hello authors, I am currently evaluating the UFO model for co-saliency detection. Could you please share with me the test set you used for evaluating model performance for co-saliency detection. Is that part of the three datasets: CoCA, Cosal2015, CoSoD3k or the entire datasets you use for testing? Thanks.