What makes a good detector? --- structured priors for learning from few examples
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part V
No bias left behind: covariate shift adaptation for discriminative 3d pose estimation
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part IV
Object class detection: A survey
ACM Computing Surveys (CSUR)
| Hi-index | 0.00 |
Our objective is transfer training of a discriminatively trained object category detector, in order to reduce the number of training images required. To this end we propose three transfer learning formulations where a template learnt previously for other categories is used to regularize the training of a new category. All the formulations result in convex optimization problems. Experiments (on PASCAL VOC) demonstrate significant performance gains by transfer learning from one class to another (e.g. motorbike to bicycle), including one-shot learning, specialization from class to a subordinate class (e.g. from quadruped to horse) and transfer using multiple components. In the case of multiple training samples it is shown that a detection performance approaching that of the state of the art can be achieved with substantially fewer training samples.