We present an approach to low-level vision that combines two main ideas: the use of convolutional networks as an image processing architecture and an unsupervised learning procedu...
1 In web-related applications of image categorization, it is desirable to derive an interpretable classification rule with high accuracy. Using the bag-of-words representation and...
Sebastian Nowozin, Koji Tsuda, Takeaki Uno, Taku K...