A Theory of Generative ConvNet

Authors: Jianwen Xie, Yang Lu, Song-Chun Zhu, Yingnian Wu

ICML 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental 7. Synthesis and Reconstruction. We show that the generative Conv Net is capable of learning and generating realistic natural image patterns. Such an empirical proof of concept validates the generative capacity of the model. We also show that contrastive divergence learning can indeed reconstruct the observed images, thus empirically validating Proposition 3.
Researcher Affiliation Academia Jianwen Xie JIANWEN@UCLA.EDU Yang Lu YANGLV@UCLA.EDU Song-Chun Zhu SCZHU@STAT.UCLA.EDU Ying Nian Wu YWU@STAT.UCLA.EDU Department of Statistics, University of California, Los Angeles, CA, USA
Pseudocode Yes Algorithm 1 Learning and sampling algorithm
Open Source Code Yes The code and training images can be downloaded from the project page: http://www.stat.ucla.edu/ ywu/ Generative Conv Net/main.html
Open Datasets Yes The code and training images can be downloaded from the project page: http://www.stat.ucla.edu/ ywu/ Generative Conv Net/main.html
Dataset Splits No No specific dataset splits for training, validation, or test sets were explicitly provided. The paper mentions 'training images' but does not specify a validation set or its proportion.
Hardware Specification No No specific hardware details (e.g., GPU/CPU models, memory, or cloud instances) used for running experiments were mentioned.
Software Dependencies No The code in our experiments is based on the Mat Conv Net package of (Vedaldi & Lenc, 2015). This mentions a software package but does not provide specific version numbers for it or any other dependencies.
Experiment Setup Yes We use M = 16 parallel chains for Langevin sampling. The number of Langevin iterations between every two consecutive updates of parameters is L = 10. With each new added layer, the number of learning iterations is T = 700. ... The first layer has 100 15 15 filters with sub-sampling size of 3. The second layer has 64 5 5 filters with sub-sampling size of 1. The third layer has 30 3 3 filters with sub-sampling size of 1. ... The number of learning iterations is T = 1200. Starting from the observed images, the number of Langevin iterations is L = 1.