2012 · 173 citations · 32 references
ComputingComputer ScienceComputer VisionMachine LearningMachine VisionImage ClassificationLarge-scale OptimizationObject RecognitionPattern RecognitionRepresentation LearningVisual SemanticsAccuracyInformation GainInformation-gain MaximizationLarge-scale ClassificationLarge-scale Computer VisionObject ClassificationReward Trade-offsSemantic Hierarchy
As visual recognition scales up to ever larger numbers of categories, maintaining high accuracy is increasingly difficult. In this work, we study the problem of optimizing accuracy-specificity trade-offs in large scale recognition, motivated by the observation that object categories form a semantic hierarchy consisting of many levels of abstraction. A classifier can select the appropriate level, trading off specificity for accuracy in case of uncertainty. By optimizing this trade-off, we obtain classifiers that try to be as specific as possible while guaranteeing an arbitrarily high accuracy. We formulate the problem as maximizing information gain while ensuring a fixed, arbitrarily small error rate with a semantic hierarchy. We propose the Dual Accuracy Reward Trade-off Search (DARTS) algorithm and prove that, under practical conditions, it converges to an optimal solution. Experiments demonstrate the effectiveness of our algorithm on datasets ranging from 65 to over 10,000 categories.
32
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
Scalable Recognition with a Vocabulary Tree
D. Nistér, Henrik Stewénius · 2006 · 3.6K citations
SUN database: Large-scale scene recognition from abbey to zoo
Jianxiong Xiao, James Hays, Krista A. Ehinger et al. · 2010 · 3.2K citations · Full text
Locality-constrained Linear Coding for image classification
Jinjun Wang, Kai Yu, Fengjun Lv et al. · 2010 · 3.1K citations
ImageNet: A large-scale hierarchical image database
Jia Deng, Wei Dong, R. Socher et al. · 2009 IEEE Conference on Computer Vision and Pattern Recognition · 2009 · 2.9K citations