How the parameters are learnt from features in unannotated images

YihongSun / Bayesian-Amodal

[CVPR 2022] Amodal Segmentation through Out-of-Task and Out-of-Distribution Generalization with a Bayesian Model

MIT License

22 stars 5 forks source link

How the parameters are learnt from features in unannotated images #9

Closed FedericaGielen closed 7 months ago

FedericaGielen commented 10 months ago

123 I am confused about how the parameters are learnt from features in unannotated images in the occlusion modeling.

YihongSun commented 10 months ago

Since the goal is to perform the outlier process for occlusion handling, the features for occlusion modeling (loaded here) intend to model the average statistics across the natural images. Therefore, it does not need to be learned, and can simply be computed as the mean feature of randomly sampled natural images.