对抗性分数身份蒸馏：一步内迅速超越教师模型
Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Step
AI总结：
本文提出SiDA方法，通过引入真实图像和对抗损失改进分数身份蒸馏，利用分数网络编码器作为判别器，在单步生成中显著提升效率与质量，超越教师模型EDM2-XXL。
摘要：
分数身份蒸馏（Score identity Distillation, SiD）是一种无数据方法，仅利用预训练扩散模型而无需任何训练数据，便在图像生成中实现了SOTA性能。然而，其最终性能受限于预训练模型在扩散过程不同阶段捕捉真实数据分数的准确度。本文提出SiDA（带有对抗损失的SiD），通过引入真实图像和对抗损失，不仅提升了生成质量，还提高了蒸馏效率。SiDA利用生成器分数网络中的编码器作为判别器，以区分真实图像与SiD生成的图像。对抗损失在每个GPU内进行批归一化，随后与原始SiD损失结合。这种整合有效地将每个GPU批次的平均“伪造度”融入基于像素的SiD损失中，使SiDA能够蒸馏出单步生成器。SiDA在从零开始蒸馏时收敛速度显著快于前代，并在从预蒸馏的SiD生成器进行微调时迅速提升原始模型性能。该单步对抗蒸馏方法在蒸馏EDM扩散模型时创下生成性能新基准，在ImageNet 64x64上达到FID分数1.110。在蒸馏于ImageNet 512x512上训练的EDM2模型时，SiDA甚至超越了最大的教师模型EDM2-XXL，后者在使用无分类器引导（CFG）和63个生成步时FID为1.81。相比之下，SiDA在无CFG且单步生成下，XS尺寸FID为2.156，S为1.669，M为1.488，L为1.413，XL为1.379，XXL为1.366。这些结果凸显了所有模型尺寸的显著改进。代码见https://github.com/mingyuanzhou/SiD/tree/sida。
英文摘要：
Score identity Distillation (SiD) is a data-free method that has achieved SOTA performance in image generation by leveraging only a pretrained diffusion model, without requiring any training data. However, its ultimate performance is constrained by how accurate the pretrained model captures the true data scores at different stages of the diffusion process. In this paper, we introduce SiDA (SiD with Adversarial Loss), which not only enhances generation quality but also improves distillation efficiency by incorporating real images and adversarial loss. SiDA utilizes the encoder from the generator's score network as a discriminator, allowing it to distinguish between real images and those generated by SiD. The adversarial loss is batch-normalized within each GPU and then combined with the original SiD loss. This integration effectively incorporates the average "fakeness" per GPU batch into the pixel-based SiD loss, enabling SiDA to distill a single-step generator. SiDA converges significantly faster than its predecessor when distilled from scratch, and swiftly improves upon the original model's performance during fine-tuning from a pre-distilled SiD generator. This one-step adversarial distillation method establishes new benchmarks in generation performance when distilling EDM diffusion models, achieving FID scores of 1.110 on ImageNet 64x64. When distilling EDM2 models trained on ImageNet 512x512, our SiDA method surpasses even the largest teacher model, EDM2-XXL, which achieved an FID of 1.81 using classifier-free guidance (CFG) and 63 generation steps. In contrast, SiDA achieves FID scores of 2.156 for size XS, 1.669 for S, 1.488 for M, 1.413 for L, 1.379 for XL, and 1.366 for XXL, all without CFG and in a single generation step. These results highlight substantial improvements across all model sizes. Our code is available at https://github.com/mingyuanzhou/SiD/tree/sida.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
