In defence of negative mining for annotating weakly labelled data
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
Weakly-supervised multi-class object detection using multi-type 3D features
Proceedings of the 21st ACM international conference on Multimedia
| Hi-index | 0.00 |
A conventional approach to learning object detectors uses fully supervised learning techniques which assumes that a training image set with manual annotation of object bounding boxes are provided. The manual annotation of objects in large image sets is tedious and unreliable. Therefore, a weakly supervised learning approach is desirable, where the training set needs only binary labels regarding whether an image contains the target object class. In the weakly supervised approach a detector is used to iteratively annotate the training set and learn the object model. We present a novel weakly supervised learning framework for learning an object detector. Our framework incorporates a new initial annotation model to start the iterative learning of a detector and a model drift detection method that is able to detect and stop the iterative learning when the detector starts to drift away from the objects of interest. We demonstrate the effectiveness of our approach on the challenging PASCAL 2007 dataset.