Diffusion Rejection Sampling
Authors: Byeonghu Na, Yeongmin Kim, Minsang Park, Donghyeok Shin, Wanmo Kang, Il-Chul Moon
ICML 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Empirical results demonstrate the state-of-the-art performance of Diff RS on the benchmark datasets and the effectiveness of Diff RS for fast diffusion samplers and large-scale text-to-image diffusion models. |
| Researcher Affiliation | Collaboration | 1Department of Industrial & Systems Engineering, KAIST, Daejeon, Republic of Korea 2summary.ai, Daejeon, Republic of Korea. Correspondence to: Il-Chul Moon <icmoon@kaist.ac.kr>, Byeonghu Na <byeonghu.na@kaist.ac.kr>. |
| Pseudocode | Yes | Algorithm 1 One Step Diff RS (t, xt+1, Lt+1), Algorithm 2 Re-initialization(t + 1, xt), Algorithm 3 Diffusion Rejection Sampling (Diff RS) |
| Open Source Code | Yes | Our code is available at https: //github.com/aailabkaist/Diff RS. |
| Open Datasets | Yes | CIFAR-10 (Krizhevsky, 2009), and Image Net 64 64 and 256 256 (Deng et al., 2009)., COCO (Lin et al., 2014) |
| Dataset Splits | No | The paper uses standard benchmark datasets like CIFAR-10 and ImageNet, which typically have predefined splits. However, it does not explicitly state the specific train/validation/test split percentages, sample counts, or the methodology for creating these splits within the paper for its experiments. |
| Hardware Specification | Yes | Our discriminator is trained on a single NVIDIA Ge Force RTX 4090 GPU using CUDA 11.8 and Py Torch 1.12 versions., For the benchmark datasets, we utilize a single NVIDIA Ge Force RTX 4090 GPU, CUDA 11.8, and Py Torch 1.12. For the text-to-image generation, we use a single NVIDIA L40S GPU with CUDA 11.8 and Py Torch 2.1. |
| Software Dependencies | Yes | Our discriminator is trained on a single NVIDIA Ge Force RTX 4090 GPU using CUDA 11.8 and Py Torch 1.12 versions., For the benchmark datasets, we utilize a single NVIDIA Ge Force RTX 4090 GPU, CUDA 11.8, and Py Torch 1.12. For the text-to-image generation, we use a single NVIDIA L40S GPU with CUDA 11.8 and Py Torch 2.1. |
| Experiment Setup | Yes | Table 5. Configurations of the discriminator., Batch size 128, # Epoch 60, Table 6. Configuration details for each experimental result., Rejection percentile γ, Max. iteration K |