Style Memory: Making a Classifier Network Generative
نویسندگان
چکیده
Deep networks have shown great performance in classification tasks. However, the parameters learned by the classifier networks usually discard stylistic information of the input, in favour of information strictly relevant to classification. We introduce a network that has the capacity to do both classification and reconstruction by adding a “style memory” to the output layer of the network. We also show how to train such a neural network as a deep multi-layer autoencoder, jointly minimizing both classification and reconstruction losses. The generative capacity of our network demonstrates that the combination of style-memory neurons with the classifier neurons yield good reconstructions of the inputs when the classification is correct. We further investigate the nature of the style memory, and how it relates to composing digits and letters. Finally, we propose that this architecture enables the bidirectional flow of information used in predictive coding, and that such bidirectional networks can help mitigate against being fooled by ambiguous or adversarial input.
منابع مشابه
Style Transfer for Anime Sketches with Enhanced Residual U-net and Auxiliary Classifier GAN
Recently, with the revolutionary neural style transferring methods [1, 3, 4, 8, 17], creditable paintings can be synthesized automatically from content images and style images. However, when it comes to the task of applying a painting’s style to a anime sketch, these methods will just randomly colorize sketch lines as outputs (fig. 7) and fail in the main task: specific style tranfer. In this p...
متن کاملDeepWriting: Making Digital Ink Editable via Deep Generative Modeling
Digital ink promises to combine the flexibility and aesthetics of handwriting and the ability to process, search and edit digital text. Character recognition converts handwritten text into a digital representation, albeit at the cost of losing personalized appearance due to the technical difficulties of separating the interwoven components of content and style. In this paper, we propose a novel...
متن کاملNeural Stain-Style Transfer Learning using GAN for Histopathological Images
Performance of data-driven network for tumor classification varies with stain-style of histopathological images. This article proposes the stain-style transfer (SST) model based on conditional generative adversarial networks (GANs) which is to learn not only the certain color distribution but also the corresponding histopathological pattern. Our model considers feature-preserving loss in additi...
متن کاملFrom source to target and back: symmetric bi-directional adaptive GAN
The effectiveness of generative adversarial approaches in producing images according to a specific style or visual domain has recently opened new directions to solve the unsupervised domain adaptation problem. It has been shown that source labeled images can be modified to mimic target samples making it possible to train directly a classifier in the target domain, despite the original lack of a...
متن کاملVoice Impersonation using Generative Adversarial Networks
Voice impersonation is not the same as voice transformation, although the latter is an essential element of it. In voice impersonation, the resultant voice must convincingly convey the impression of having been naturally produced by the target speaker, mimicking not only the pitch and other perceivable signal qualities, but also the style of the target speaker. In this paper, we propose a novel...
متن کامل