Faster R-CNN Scene Specialization with a Sequential Monte-Carlo Framework
Authors:
- Ala MhallaAMAla Mhalla
- Houda MaamatouHMHouda Maamatou
- Thierry ChateauTCThierry Chateau
- Sami GazzahSGSami Gazzah
- Najoua Essoukri Ben AmaraNANajoua Essoukri Ben Amara
- 1 November 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
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.Keywords
This publication has 18 references indexed in Scilit:
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Transductive Transfer Learning to Specialize a Generic Classifier Towards a Specific Scene2016
- Deep transfer metric learning2015
- Domain adaption of vehicle detector based on convolutional neural networksInternational Journal of Control, Automation, and Systems, 2015
- Caffe2014
- Efficient Non-iterative Domain Adaptation of Pedestrian Detectors to Video Scenes2014
- DeepFace: Closing the Gap to Human-Level Performance in Face Verification2014
- Scene-Specific Pedestrian Detection for Static Video SurveillanceIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Learning hierarchical representations for face verification with convolutional deep belief networks2012
- Unsupervised and transfer learning challenge2011