2011 · 160 citations · 14 references
ComputingComputer ScienceComputer VisionMachine LearningMachine VisionImage AnnotationObject DetectionObject RecognitionDetectorsIterative LearningLabelsModel AnnotationWeakly Supervised AnnotationWeakly Supervised LearningWeakly Supervised Object Detection
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.
14
Genetic algorithms in search, optimization, and machine learning
Choice Reviews Online · 1989 · 49.3K citations
Object recognition from local scale-invariant features
David Lowe · 1999 · 16.2K citations
Support Vector Machines for Multiple-Instance Learning
Stuart Andrews, Ioannis Tsochantaridis, Thomas Hofmann · 2002 · 1.4K citations