JFM让生成模型同时做分类和图像生成，且结果可信。
Joint Flow Matching for Generator-Consistent Classification
- 用相反角色设计变量在时间起点终点的映射，实现联合分布一致性。
- 在条件数据集上达到竞品水平准确率，且置信度无需事后校准。
- 适合需要解释性的判别-生成统一模型的研究者或应用。
我们提出联合流匹配（JFM），一种针对多变量连续归一化流的训练框架。标准流匹配同时将变量从噪声映射到数据，缺乏自然机制实现正向与反向条件推断。JFM通过在时间端点为每个变量分配相反角色解决此问题。我们证明，JFM生成的联合分布具有性质：正向或反向积分均为同一联合分布的条件分布。我们在联合分类与生成任务中探索该一致性，作为判别-生成模型可解释性的基础。在条件数据集上的实验表明，JFM实现了与竞品相当的分类准确率，且置信度评分固有地良好校准，无需事后校准，并能生成与分类器一致的图像。
原文摘要 · Abstract (English)
We introduce Joint Flow Matching (JFM), a training framework for continuous normalising flows over multiple variables. Standard flow matching transports variables from noise to data simultaneously, offering no natural mechanism for forward and reverse conditional inference from a shared joint model. JFM resolves this by assigning opposite roles to each variable at the temporal endpoints. We prove that JFM produces a consistent joint distribution where that forward or reverse integration are conditionals of the same joint. We explore this consistency in the context of joint classification and generation as the basis for interpretability in discriminative-generative models. We validate JFM on conditional datasets producing competitive accuracy with inherently well-calibrated confidence scores without post-hoc calibration, and classifier-consistent image generation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。