Rethinking Conditional Diffusion Sampling with Progressive Guidance

Authors: Anh-Dung Dinh, Daochang Liu, Chang Xu

NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental 6 Experiments", "Table 1: Pro G helps to achieve better IS/FID/s FID in general.", "Extensive experiments are conducted on CIFAR10, Image Net (64x64, 128x128, 256x256).
Researcher Affiliation Academia Anh-Dung Dinh School of Computer Science The University of Sydney dinhanhdung1996@gmail.com", "Daochang Liu School of Computer Science The University of Sydney daochang.liu@sydney.edu.au", "Chang Xu School of Computer Science The University of Sydney c.xu@sydney.edu.au
Pseudocode No The paper does not include a dedicated section or figure explicitly labeled 'Pseudocode' or 'Algorithm'.
Open Source Code Yes Source code is available at: https://github.com/dungdinhanh/prog-guided-diffusion.
Open Datasets Yes Extensive experiments are conducted on CIFAR10, Image Net (64x64, 128x128, 256x256).
Dataset Splits No The paper mentions the use of datasets like ImageNet and CIFAR10, but it does not explicitly provide specific details on the train/validation/test dataset splits (e.g., percentages or sample counts) used for its own experiments.
Hardware Specification No The paper mentions that 'The AI training platform supporting this work was provided by High-Flyer AI (Hangzhou High-Flyer AI Fundamental Research Co., Ltd.)' but does not specify any particular hardware components like GPU or CPU models.
Software Dependencies No The paper references various models and frameworks (e.g., ADM, IDDPM, CLIP) but does not provide specific software dependencies with version numbers (e.g., Python version, library versions) for reproducibility.
Experiment Setup Yes Setup. Extensive experiments are conducted on CIFAR10, Image Net (64x64, 128x128, 256x256). We denote Progressive Guidance (Pro G) as our proposed method, which is first evaluated on ADM [11] and IDDPM [3] to verify our claims on improving the performance of the vanilla guidance method." and "Table 5: γ sensitivity comparision." and "When increasing the guidance scale, our proposed method mostly has a slower degeneration rate in FID and Recall than the vanilla guidance.