arXiv (Cornell University) · 2014 · 104 citations · 26 references
ComputingComputer ScienceComputer VisionMachine LearningMachine VisionDeep LearningObject DetectionObject RecognitionPattern RecognitionScene UnderstandingVisual DetectionPatternsSubmodular MaximizationSubmodular OptimizationWeakly Supervised Image ClassificationWeakly Supervised LearningWeakly Supervised Object DetectionWeakly Supervised Object Recognition
The increasing prominence of weakly labeled data nurtures a growing demand for object detection methods that can cope with minimal supervision. We propose an approach that automatically identifies discriminative configurations of visual patterns that are characteristic of a given object class. We formulate the problem as a constrained submodular optimization problem and demonstrate the benefits of the discovered configurations in remedying mislocalizations and finding informative positive and negative training examples. Together, these lead to state-of-the-art weakly-supervised detection results on the challenging PASCAL VOC dataset.
26
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Ross Girshick, Jeff Donahue, Trevor Darrell et al. · 2014 · 31.8K citations
Selective Search for Object Recognition
Jasper Uijlings, Koen E. A. van de Sande, Theo Gevers et al. · International Journal of Computer Vision · 2013 · 6.1K citations · Full text