Uni-DAD: Unified Distillation and Adaptation of Diffusion Models for Few-step Few-shot Image Generation
Uni-DAD: 集成扩散模型的蒸馏与适应以实现少步少样本图像生成
机构 * LIVIA, ILLS, ETS(LIVIA、ILLs、ETS)
专题命中 效率与蒸馏 :image generation(title,abstract);diffusion(title,abstract);分类 cs.CV
AI总结 Uni-DAD通过统一蒸馏与适应流程,提升少样本图像生成质量与多样性,采用双域分布匹配和多头GAN损失,实现单阶段高效生成。
Comments Accepted at IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026