Author:
Han Tian,Lu Yang,Zhu Song-Chun,Wu Ying Nian
Abstract
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.
Publisher
Association for the Advancement of Artificial Intelligence (AAAI)
Cited by
6 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Meta Perturbed Re-Id Defense;2023 IEEE International Conference on Multimedia and Expo (ICME);2023-07
2. Diverse 3D Hand Gesture Prediction from Body Dynamics by Bilateral Hand Disentanglement;2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR);2023-06
3. A General Divergence Modeling Strategy for Salient Object Detection;Computer Vision – ACCV 2022;2023
4. An Energy-Based Prior for Generative Saliency;IEEE Transactions on Pattern Analysis and Machine Intelligence;2023
5. Deep Image Models;Computer Vision;2023