Learning Class-to-Image Distance with Object Matchings
Autor: | Guang-Tong Zhou, Greg Mori, Tian Lan, Weilong Yang |
---|---|
Rok vydání: | 2013 |
Předmět: |
Contextual image classification
Standard test image business.industry Binary image ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Pattern recognition Pascal (programming language) Automatic image annotation Image texture One-class classification Computer vision Artificial intelligence Best matching business computer computer.programming_language Mathematics |
Zdroj: | CVPR |
Popis: | We conduct image classification by learning a class-to-image distance function that matches objects. The set of objects in training images for an image class are treated as a collage. When presented with a test image, the best matching between this collage of training image objects and those in the test image is found. We validate the efficacy of the proposed model on the PASCAL 07 and SUN 09 datasets, showing that our model is effective for object classification and scene classification tasks. State-of-the-art image classification results are obtained, and qualitative results demonstrate that objects can be accurately matched. |
Databáze: | OpenAIRE |
Externí odkaz: |