{"ID":2868034,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.16897","arxiv_id":"2509.16897","title":"PRISM: Precision-Recall Informed Data-Free Knowledge Distillation via Generative Diffusion","abstract":"Data-free knowledge distillation (DFKD) transfers knowledge from a teacher to a student without access to the real in-distribution (ID) data. While existing methods perform well on small-scale images, they suffer from mode collapse when synthesizing large-scale images, resulting in limited knowledge transfer. Recently, leveraging advanced generative models to synthesize photorealistic images has emerged as a promising alternative. Nevertheless, directly using off-the-shelf diffusion to generate datasets faces the precision-recall challenges: 1) ensuring synthetic data aligns with the real distribution, and 2) ensuring coverage of the real ID manifold. In response, we propose PRISM, a precision-recall informed synthesis method. Specifically, we introduce Energy-guided Distribution Alignment to avoid the generation of out-of-distribution samples, and design the Diversified Prompt Engineering to enhance coverage of the real ID manifold. Extensive experiments on various large-scale image datasets demonstrate the superiority of PRISM. Moreover, we demonstrate that models trained with PRISM exhibit strong domain generalization.","short_abstract":"Data-free knowledge distillation (DFKD) transfers knowledge from a teacher to a student without access to the real in-distribution (ID) data. While existing methods perform well on small-scale images, they suffer from mode collapse when synthesizing large-scale images, resulting in limited knowledge transfer. Recently,...","url_abs":"https://arxiv.org/abs/2509.16897","url_pdf":"https://arxiv.org/pdf/2509.16897v1","authors":"[\"Xuewan He\",\"Jielei Wang\",\"Zihan Cheng\",\"Yuchen Su\",\"Shiyue Huang\",\"Guoming Lu\"]","published":"2025-09-21T03:16:07Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}