Question about semi-supervised cross dataset evaluation about sted-gaze HOT 2 CLOSED

Hi,

1. the joint distrubution estimation and sampling is implemented here:

   STED-gaze/dataset.py

   Line 85 in add7936

   self.kernel = stats.gaussian_kde(sample)

   
   And, yes, this step is to avoid unrealistic gaze direction and head pose combinations.

2. First, usually, labeled data is considered expensive and unlabeled data can almost be seen as free. We want to test whether we can use unlabeled data to boost accuracy. Ideally, we can also use the entire GazeCapture dataset plus facial image datasets without gaze labels. But the preprocessing would be cumbersome to do. Therefore, we used a subset of GazeCapture as the unlabeled dataset to prove the concept.

In this case, is loss for image generation is still applied to the model, but explicit gaze and head labels are not applied except for the sampled images?

Yes this is correct.

from sted-gaze.

Thank you for your quick and detailed response! :)

from sted-gaze.