Abstract
We conduct image classifification by learning a class-toimage 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 effificacy of the proposed model on the PASCAL 07 and SUN 09 datasets, showing that our model is effective for object classifification and scene classifification tasks. State-of-the-art image classi- fification results are obtained, and qualitative results demonstrate that objects can be accurately matched