Tracing Hyperparameter Dependencies for Model Parsing via Learnable Graph Pooling Network

arXiv:2312.02224v2 Announce Type: replace
Abstract: Model Parsing defines the research task of predicting hyperparameters of the generative model (GM), given a generated image as input. Since a diverse set of hyperparameters is jointly employed by the generative model, and dependencies often exist among them, it is crucial to learn these hyperparameter dependencies for the improved model parsing performance. To explore such important dependencies, we propose a novel model parsing method called Learnable Graph Pooling Network (LGPN). Specifically, we transform model …

abstract arxiv cs.cv dependencies diverse generated generative graph hyperparameter image learn network parsing pooling research set them tracing type via