An Efficient Explorative Sampling Considering the Generative Boundaries of Deep Generative Neural Networks
This work addresses the problem of interpretability in generative models for researchers and practitioners, but it is incremental as it builds on existing sampling methods.
The paper tackles the challenge of understanding the image generation mechanism in deep generative neural networks by introducing an explorative sampling algorithm that efficiently gathers samples with identical attributes from a query image, revealing internal layer characteristics and finding more homogeneous, model-specific samples compared to ε-based sampling variations.
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.