Abstract : Transfer learning approaches have shown interesting results by using knowledge from source domains to learn a specialized classifier/detector for a target domain containing unlabeled data or only a few labeled samples. In this paper, we present a new transductive transfer learning framework based on a sequential Monte Carlo filter to specialize a generic classifier towards a specific scene. The proposed framework utilizes different strategies and approximates iteratively the hidden target distribution as a set of samples in order to learn a specialized classifier. These training samples are selected from both source and target domains according to their weight importance, which indicates that they belong to the target distribution. The resulting classifier is applied to pedestrian and car detection on several challenging traffic scenes. The experiments have demonstrated that our solution improves and outperforms several state of the art's specialization algorithms on public datasets.
https://hal.archives-ouvertes.fr/hal-01653428
Contributeur : Thierry Chateau
<>
Soumis le : jeudi 28 février 2019 - 16:50:24
Dernière modification le : vendredi 8 mars 2019 - 11:42:06
Houda Maamatou, Thierry Chateau, Sami Gazzah, Yann Goyat, Najoua Essoukri Ben Amara. Sequential Monte Carlo filter based on multiple strategies for a scene specialization classifier. EURASIP Journal on Image and Video Processing, Springer, 2016, 2016 (1), 〈10.1186/s13640-016-0143-4〉. 〈hal-01653428〉
