search

alexanderkroner / saliency

Contextual Encoder-Decoder Network for Visual Saliency Prediction [Neural Networks 2020]
MIT License
172 stars 46 forks source link

saliency metric evaluation on test dataset #17

Closed shilpamathew14 closed 2 years ago

shilpamathew14 commented 2 years ago

Thank you Sir for the wonderful code you have made here... thoroughly worked and clearly coded..

Sir, i tried to train on salicon and tested on (say) osie dataset. The predicted saliency maps are obtained on the results folder perfectly. I would like to know how i will be able to compute different saliency metric (say kld, AUC-Judd) between the predicted and true maps via code frame? How can I implement an evaluate function between them? It would be great if you can provide help towards this..

EricPengShuai commented 2 years ago

@shilpamathew14 Maybe you can try another github code: https://github.com/matthias-k/pysaliency, which can be found on MIT saliency website.

alexanderkroner commented 2 years ago

Sorry for the late reply! To evaluate predicted saliency maps against the ground truth, I used this repository which implements commonly used metrics in MATLAB: https://github.com/cvzoya/saliency/tree/master/code_forMetrics

If you're looking for a solution in Python, I can also recommend the pysaliency package: https://github.com/matthias-k/pysaliency

shilpamathew14 commented 2 years ago

Thanks a lot for the responses. I have been trying with pysaliency these days and it has been working good.... Thank you for the suggestions.