PGNet
PGNet copied to clipboard
iCVTEAM
Pyramid Grafting Network for One-Stage High Resolution Saliency Detection. CVPR 2022
> A total of 5,920 images were manually selected from websites (e.g. Flickr Pixabay) with free copyright. Could you list the licenses of each individual image and where they are...
Thank you for your nice work. I had some problems with the code, my model predictions were all grey with a little bit of texture. What might be the cause...
Thank you for your nice work.I noticed in the paper that S3 and S4 of the Swin-Transformer branch have the same size and are not downsampled. What is the reason?
tkank you for you nice work. could you tell us what evaluation code do you use? please
Thank you for your nice work. I would like to know how to visualize the feature maps，like figure 4. Thank you very much.
Hey Great work! well done! The [google drive link](https://drive.google.com/drive/folders/1hXwCvrdmvkaRePXWPTw5tjFXmrrzHPtt) contains the model that was trained on DUTS + HR, named Ours-DH. Can you please share the Ours-UH model as well?
1. Add/update instructions about downloading, renaming and moving models to appropriate folders. 2. Add required folders to make it clearer. 3. Add test_images.py for running on custom images.
Hello! @iCVTEAM, Have you ever consider to upload this model to [huggingFace](https://huggingface.com/) 🤗 to everybody could run the model using the transformers library and build a demo to test it??...
