SMC Faster R-CNN: Toward a scene-specialized multi-object detector
This work addresses the domain adaptation problem for object detection in specific scenes like traffic, offering an incremental improvement over existing specialization methods.
The paper tackles the problem of generic object detectors performing poorly on specific scenes by proposing a Sequential Monte Carlo (SMC) filter-based transfer learning method to specialize Faster R-CNN for target scenes, achieving encouraging results on traffic datasets compared to state-of-the-art frameworks.
Generally, the performance of a generic detector decreases significantly when it is tested on a specific scene due to the large variation between the source training dataset and the samples from the target scene. To solve this problem, we propose a new formalism of transfer learning based on the theory of a Sequential Monte Carlo (SMC) filter to automatically specialize a scene-specific Faster R-CNN detector. The suggested framework uses different strategies based on the SMC filter steps to approximate iteratively the target distribution as a set of samples in order to specialize the Faster R-CNN detector towards a target scene. Moreover, we put forward a likelihood function that combines spatio-temporal information extracted from the target video sequence and the confidence-score given by the output layer of the Faster R-CNN, to favor the selection of target samples associated with the right label. The effectiveness of the suggested framework is demonstrated through experiments on several public traffic datasets. Compared with the state-of-the-art specialization frameworks, the proposed framework presents encouraging results for both single and multi-traffic object detections.