What mechanisms causes GAN's entanglement? Although developing disentangled GAN has attracted sufficient attention, it is unclear how entanglement is originated by GAN transformation. We in this research propose a difference-in-difference (DID) counterfactual framework to design experiments for analyzing the entanglement mechanism in on of the Progressive-growing GAN (PG-GAN). Our experiment clarify the mechanisms how pixel normalization causes PG-GAN entanglement during a input-unit-ablation transformation. We discover that pixel normalization causes object entanglement by in-painting the area occupied by ablated objects. We also discover the unit-object relation determines whether and how pixel normalization causes objects entanglement. Our DID framework theoretically guarantees that the mechanisms that we discover is solid, explainable and comprehensively.
Cite
@article{arxiv.2010.08402,
title = {Difference-in-Differences: Bridging Normalization and Disentanglement in PG-GAN},
author = {Xiao Liu and Jiajie Zhang and Siting Li and Zuotong Wu and Yang Yu},
journal= {arXiv preprint arXiv:2010.08402},
year = {2020}
}