2010 · 220 citations · 24 references
ComputingComputer ScienceComputer VisionInformation RetrievalMachine LearningClassificationImage AnnotationImage ClassificationImage RetrievalObject RecognitionSupervised LearningDomain AdaptationGeneralization ErrorObject ClassificationWeakly Supervised Image ClassificationWeakly Supervised LearningWeakly Supervised Object Recognition
Most current image categorization methods require large collections of man-ually annotated training examples to learn accurate visual recognition models. The time-consuming human labeling effort effectively limits these approaches to recognition problems involving a small number of different object classes. In or-der to address this shortcoming, in recent years several authors have proposed to learn object classifiers from weakly-labeled Internet images, such as photos re-trieved by keyword-based image search engines. While this strategy eliminates the need for human supervision, the recognition accuracies of these methods are considerably lower than those obtained with fully-supervised approaches, because of the noisy nature of the labels associated to Web data. In this paper we investigate and compare methods that learn image classifiers by combining very few manually annotated examples (e.g., 1-10 images per class) and a large number of weakly-labeled Web photos retrieved using keyword-based image search. We cast this as a domain adaptation problem: given a few strongly-labeled examples in a target domain (the manually annotated examples) and many source domain examples (the weakly-labeled Web photos), learn classifiers yield-ing small generalization error on the target domain. Our experiments demonstrate that, for the same number of strongly-labeled examples, our domain adaptation approach produces significant recognition rate improvements over the best pub-lished results (e.g., 65 % better when using 5 labeled training examples per class) and that our classifiers are one order of magnitude faster to learn and to evaluate than the best competing method, despite our use of large weakly-labeled data sets. 1
24
ImageNet: A large-scale hierarchical image database
Jia Deng, Wei Dong, Richard Socher et al. · 2009 IEEE Conference on Computer Vision and Pattern Recognition · 2009 · 61.8K citations
The Pascal Visual Object Classes (VOC) Challenge
Mark Everingham, Luc Van Gool, Christopher K. I. Williams et al. · International Journal of Computer Vision · 2009 · 19.5K citations · Full text
Recognition-by-components: A theory of human image understanding.
Irving Biederman · Psychological Review · 1987 · 5.6K citations
LabelMe: A Database and Web-Based Tool for Image Annotation
Bryan Russell, Antonio Torralba, Kevin Murphy et al. · International Journal of Computer Vision · 2007 · 4.2K citations · Full text