Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2312.02224 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909372925345792 |
|---|---|
| author | Guo, Xiao Asnani, Vishal Liu, Sijia Liu, Xiaoming |
| author_facet | Guo, Xiao Asnani, Vishal Liu, Sijia Liu, Xiaoming |
| contents | 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 parsing into a graph node classification task, using graph nodes and edges to represent hyperparameters and their dependencies, respectively. Furthermore, LGPN incorporates a learnable pooling-unpooling mechanism tailored to model parsing, which adaptively learns hyperparameter dependencies of GMs used to generate the input image. We also extend our proposed method to CNN-generated image detection and coordinate attacks detection. Empirically, we achieve state-of-the-art results in model parsing and its extended applications, showing the effectiveness of our method. Our source code are available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_02224 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Tracing Hyperparameter Dependencies for Model Parsing via Learnable Graph Pooling Network Guo, Xiao Asnani, Vishal Liu, Sijia Liu, Xiaoming Computer Vision and Pattern Recognition 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 parsing into a graph node classification task, using graph nodes and edges to represent hyperparameters and their dependencies, respectively. Furthermore, LGPN incorporates a learnable pooling-unpooling mechanism tailored to model parsing, which adaptively learns hyperparameter dependencies of GMs used to generate the input image. We also extend our proposed method to CNN-generated image detection and coordinate attacks detection. Empirically, we achieve state-of-the-art results in model parsing and its extended applications, showing the effectiveness of our method. Our source code are available. |
| title | Tracing Hyperparameter Dependencies for Model Parsing via Learnable Graph Pooling Network |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2312.02224 |