An Efficient Explorative Sampling Considering the Generative Boundaries of Deep Generative Neural Networks
arXiv:1912.05827
Abstract
Deep generative neural networks (DGNNs) have achieved realistic and high-quality data generation. In particular, the adversarial training scheme has been applied to many DGNNs and has exhibited powerful performance. Despite of recent advances in generative networks, identifying the image generation mechanism still remains challenging. In this paper, we present an explorative sampling algorithm to analyze generation mechanism of DGNNs. Our method efficiently obtains samples with identical attributes from a query image in a perspective of the trained model. We define generative boundaries which determine the activation of nodes in the internal layer and probe inside the model with this information. To handle a large number of boundaries, we obtain the essential set of boundaries using optimization. By gathering samples within the region surrounded by generative boundaries, we can empirically reveal the characteristics of the internal layers of DGNNs. We also demonstrate that our algorithm can find more homogeneous, the model specific samples compared to the variations of ε-based sampling method.
arXiv commentAAAI 2020
References in corpus (8)
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Progressive Growing of GANs for Improved Quality, Stability, and Variation
- Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
- LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
- On the Number of Linear Regions of Deep Neural Networks
- On the importance of single directions for generalization
- Interpretable Convolutional Filters with SincNet
- Geometric Understanding of Deep Learning