Domain Adaptation of Deformable Part-based Models
Thesis Committee: Dr. Francesc Moreno Noguer (Dep.: Institut de Robòtica i Informàtica Industrial. CSIC/UPC, Barcelona, Spain), Dr. Joan Serrat Gual (Dep. Computer Science, UAB, Computer Vision Centre, Barcelona, Spain) & Dr. Erik Rodner (Computer Vision Group, Department for Mathematics and Computer Science. Friedrich Schiller University of Jena. Germany)
On-board pedestrian detection is crucial for Advanced Driver Assistance Systems (ADAS). An accurate classification is fundamental for vision-based pedestrian detection. The underlying assumption for learning classifiers is that the training set and the deployment environment (testing) follow the same probability distribution regarding the features used by the classifiers. However, in practice, there are different reasons that can break this constancy assumption. Accordingly, reusing existing classifiers by adapting them from the previous training environment (source domain) to the new testing one (target domain) is an approach with increasing acceptance in the computer vision community. In this thesis we focus on the domain adaptation of deformable part-based models (DPMs) for pedestrian detection. As a prof of concept, we use a computer graphic based synthetic dataset, i.e. a virtual world, as the source domain, and adapt the virtual-world trained DPM detector to various real-world dataset. We start by exploiting the maximum detection accuracy of the virtual-world trained DPM. Even though, when operating in various real-world datasets, the virtual world trained detector still suffer from accuracy degradation due to the domain gap of virtual and real worlds. We then focus on domain adaptation of DPM. At the first step, we consider single source and single target domain adaptation and propose two batch learning methods, namely A-SSVM and SA-SSVM. Later, we further consider leveraging multiple target (sub-)domains for progressive domain adaptation and propose a hierarchical adaptive structured SVM (HA-SSVM) for optimization. Finally, we extend HA-SSVM for the challenging online domain adaptation problem, aiming at making the detector to automatically adapt to the target domain online, without any human intervention. All of the proposed methods in this thesis do not require revisiting source domain data. The evaluations are done on the Caltech pedestrian detection benchmark. Results show that SA-SSVM slightly outperforms A-SSVM and avoids accuracy drops as high as 15 points when comparing with a non-adapted detector. The hierarchical model learned by HA-SSVM further boosts the domain adaptation performance. Finally, the online domain adaptation method has demonstrated that it can achieve comparable accuracy to the batch learned models while no trequiring manually label target domain examples. Domain adaptation for pedestrian detection is of paramount importance and a relatively unexplored area. We humbly hope the work in this thesis could provide foundations for future work in this area.