Alternating Back-Propagation for Generator Network
This paper proposes an alternating back-propagation algorithm for learning the generator network model. The model is a non-linear generalization of factor analysis. In this model, the mapping from the continuous latent factors to the observed signal is parametrized by a convolutional neural network. The alternating back-propagation algorithm iterates the following two steps: (1) Inferential back-propagation, which infers the latent factors by Langevin dynamics or gradient descent. (2) Learning back-propagation, which updates the parameters given the inferred latent factors by gradient descent. The gradient computations in both steps are powered by back-propagation, and they share most of their code in common. We show that the alternating back-propagation algorithm can learn realistic generator models of natural images, video sequences, and sounds. Moreover, it can also be used to learn from incomplete or indirect training data.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Learning Dynamic Generator Model by Alternating Back-Propagation Through Time
This paper studies the dynamic generator model for spatial-temporal processes such as dynamic textures and action sequences in video data. In this model, each time frame of the video sequence is generated by a generator …
Learning Feature-to-Feature Translator by Alternating Back-Propagation for Generative Zero-Shot Learning
We investigate learning feature-to-feature translator networks by alternating back-propagation as a general-purpose solution to zero-shot learning (ZSL) problems. It is a generative model-based ZSL framework. In contrast…
Zero-Shot LearningLearning Noise-Aware Encoder-Decoder from Noisy Labels by Alternating Back-Propagation for Saliency Detection
In this paper, we propose a noise-aware encoder-decoder framework to disentangle a clean saliency predictor from noisy training examples, where the noisy labels are generated by unsupervised handcrafted feature-based met…
DecoderSaliency DetectionUnified Signal Compression Using a GAN with Iterative Latent Representation Optimization
We propose a unified signal compression framework that uses a generative adversarial network (GAN) to compress heterogeneous signals. The compressed signal is represented as a latent vector and fed into a generator netwo…
Generative Adversarial NetworkImage CompressionMS-SSIMSSIMSelf-Supervised Multi-Scale Network for Blind Image Deblurring via Alternating Optimization
Blind image deblurring is a challenging low-level vision task that involves estimating the unblurred image when the blur kernel is unknown. In this paper, we present a self-supervised multi-scale blind image deblurring m…
Blind Image DeblurringDeblurringImage Deblurring