Hyunjung Shim, Kyungjune Baek
We lifted 4 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| FriedRonaldo/Primitives-PS | — | 1 of 4 |
| Function | Status | Where it lives |
|---|---|---|
| bn | Ran | FriedRonaldo/Primitives-PS/cifar/diffAug-cifar-posttrain/BigGAN.py pointer only (licence: NONE) · get_code("e9d1f7dec1c996a1") |
| GBlock | Not yet run | FriedRonaldo/Primitives-PS/cifar/diffAug-cifar-posttrain/BigGAN.py pointer only (licence: NONE) · get_code("0a15eca7a1364237") |
| Generator | Not yet run | FriedRonaldo/Primitives-PS/cifar/diffAug-cifar-posttrain/BigGAN.py pointer only (licence: NONE) · get_code("ba6617799b631163") |
| ccbn | Not yet run | FriedRonaldo/Primitives-PS/cifar/diffAug-cifar-posttrain/BigGAN.py pointer only (licence: NONE) · get_code("9222bd74a234e207") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Transfer learning for GANs successfully improves generation performance under low-shot regimes. However, existing studies show that the pretrained model using a single benchmark dataset is not generalized to various target datasets. More importantly, the pretrained model can be vulnerable to copyright or privacy risks as membership inference attack advances. To resolve both issues, we propose an effective and unbiased data synthesizer, namely Primitives-PS, inspired by the generic characteristics of natural images. Specifically, we utilize 1) the generic statistics on the frequency magnitude spectrum, 2) the elementary shape (i.e., image composition via elementary shapes) for representing the structure information, and 3) the existence of saliency as prior. Since our synthesizer only considers the generic properties of natural images, the single model pretrained on our dataset can be consistently transferred to various target datasets, and even outperforms the previous methods pretrained with the natural images in terms of Fréchet inception distance. Extensive analysis, ablation study, and evaluations demonstrate that each component of our data synthesizer is effective, and provide insights on the desirable nature of the pretrained model for the transferability of GANs.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2204.04950")
get_code_for_paper("2204.04950")
have("2204.04950")
Connect an agent — have() is free.