search

alexanderkroner / saliency

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

Question on 8 Indicators of Verification Set and Image Visualization #1

Closed mymuli closed 4 years ago

mymuli commented 4 years ago

Hi， Thank you for sharing the good idea and code. The code can be run in Python 3.5 and tensorflow 1.10.1 environments. At the same time, I have a few questions to ask.

1: How to get the results of 8 indicators in Table 1 and Table 2 on MIT300 test set and CAT2000 test set? I didn't see these eight indicators in the program.

2: How to visualize the image in the validation set? As shown in Figure 3 of the article. I don't seem to see the corresponding visualization programs or the results in color maps.

Can you give me some advice?

Thanks !

alexanderkroner commented 4 years ago

Hey, thanks for letting me know! Regarding your questions:

  1. Table 1 and 2 show the results I received after submitting my predictions to the MIT saliency benchmark (http://saliency.mit.edu). To compute the saliency metrics myself for the validation set, I used the MATLAB scripts here: https://github.com/cvzoya/saliency/tree/master/code_forMetrics

  2. For the figures I simply took the saliency maps and overlaid the input images with them using a graphics editor. I did not use any code to do so.

I hope this answers your questions!