首页>
外国专利>
Learning image categorization using related attributes
Learning image categorization using related attributes
展开▼
机译:使用相关属性学习图像分类
展开▼
页面导航
摘要
著录项
相似文献
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.
展开▼