Generative deep deconvolutional neural network for increasing and diversifying training data

摘要

Large amount of annotated images with rich variations are needed to train a deep network for detecting instance object in unstructured environment. Addressing the problem that the artificial acquisition and manual annotation is time-consuming, the generative deep deconvolutional neural network (GDDNE) to increase and diversify training data through the supervised learning strategy is created in this paper. Specifically, our network can not only generate with different styles such as shift, zoom, brightness and other superimposed transformations, but also interpolate generate the new ones between given viewpoints images in training samples. With 180 viewpoints realistic images in training samples: 30 rotation angles in plane and 6 angles of depression, our network can finally generated 1000 diversified viewpoint images and 21 kinds of data transformations for each instance object. Abundant experiments demonstrate that the remarkable performance of our generative network used in the generation task of large magnitude.