LEARNING IMAGE CATEGORIZATION USING RELATED ATTRIBUTES

摘要

A first set of attributes (e.g., style) is generated through pre-trained single column neural networks and leveraged to regularize the training process of a regularized double-column convolutional neural network (RDCNN). Parameters of the first column (e.g., style) of the RDCNN are fixed during RDCNN training Parameters of the second column (e.g., aesthetics) are fine-tuned while training the RDCNN and the learning process is supervised by the label identified by the second column (e.g., aesthetics). Thus, features of the images may be leveraged to boost classification accuracy of other features by learning a RDCNN.

主权项

1. A non-transitory computer storage medium comprising computer-useable instructions that, when used by one or more computing devices, cause the one or more computing devices to perform operations comprising:
implementing a regularized double-column convolutional neural network (RDCNN) that is trained to classify image features for a set of images; receiving an image from the set of images; fixing parameters of a first feature column of the RDCNN; utilizing attributes of the image in the first feature column to regularize training for a second feature column; identifying a class associated with the second feature column for the image.