Faster R-CNN Scene Specialization with a Sequential Monte-Carlo Framework

Authors:
  • HMHouda Maamatou
    Houda Maamatou
  • TCThierry Chateau
    Thierry Chateau
  • SGSami Gazzah
    Sami Gazzah
  • NANajoua Essoukri Ben Amara
    Najoua Essoukri Ben Amara

Abstract
The performance of the learning-based detector depends much on its training dataset and decreases rapidly when it is tested on a new scene. The reason is that in the large variations between the source training dataset and target scene. To solve this problem, we propose a novel approach to automatically specialize a generic detector to specific scene by utilizing the sequential Monte Carlo filter and the Faster R-CNN deep model. The main idea is to consider the Faster R-CNN as a function that generates realizations from the probability distribution of the object to be detected in the target sequence. Our contribution is to approximate this target probability distribution with a set of samples and an associated specialized Faster R-CNN estimated in a sequential Bayesian filter framework. The resulting algorithm is compared to the state of the art scene specialization methods on several challenging datasets, the results are very promising.

This publication has 18 references indexed in Scilit: