Learning mid-level features from object hierarchy for image classificationEIWOS
Applications of Computer Vision, 2014, Pages 235-240.
Keywords:feature extractionimage classificationimage representationlearning (artificial intelligence)binary classifiersview more (7+)
We propose a new approach for constructing mid-level visual features for image classification. We represent an image using the outputs of a collection of binary classifiers. These binary classifiers are trained to differentiate pairs of object classes in an object hierarchy. Our feature representation implicitly captures the hierarchical ...More