Visibility Estimation via Deep Label Distribution Learning
- Mofei Song ,
- Han Xu ,
- Xiao Fan Liu ,
- Qian Li
Abstract
This paper proposes an image-based visibility estimation method with
deep label distribution learning. To train an accurate model for
visibility estimation, it is important to obtain the precise ground
truth for every image. However, the ground-truth visibility is difficult
to be labeled due to its high ambiguity. To solve this problem, we
associate a label distribution to each image. The label distribution
contains all the possible visibilities with their probabilities. To
learn from such annotation, we employ a CNN-RNN model for
visibility-aware feature extraction and a conditional probability neural
network for distribution prediction. Our experiment shows that labeling
the image with visibility distribution can not only overcome the
inaccurate annotation problem, but also boost the learning performance
without the increase of training examples.