通过前瞻式计算梯度项，提升图像生成模型的分布拟合能力。
Lookahead Drifting Model
- 逐次计算多个梯度项，利用历史信息和正样本引导优化方向。
- 在CIFAR10上性能优于基线方法，玩具数据集验证有效性。
- 适合关注生成模型训练机制改进的研究者。
近期提出的漂移模型（drifting model）通过单步神经函数评估（NFE）实现了ImageNet图像生成的最先进性能。其核心思想是在每次训练迭代中计算一个漂移项，并将模型输出推向该方向。本文提出前瞻漂移模型（lookahead drifting model），在每次迭代中按顺序计算一组漂移项，每个项结合先前计算结果、正样本及模型输出进行构造。关键在于合理缩放漂移项，使其量级可比较；后期获得的漂移项能捕捉更高阶的梯度信息。模型通过加权求和所有漂移项的方向进行优化。在玩具示例与CIFAR10上的实验表明，新方法性能优于基线。
原文摘要 · Abstract (English)
Recently, a new paradigm named \emph{drifting model} has been proposed for mapping distributions, which achieves the SOTA image generation performance over ImageNet via one-step neural functional evaluation (NFE). The basic idea is to compute a drifting term at each training iteration and then push the output of the model towards the direction of the drifting term. In this paper, we propose a \emph{lookahead drifting model}. At each training iteration, we compute a set of drifting terms sequentially. Each drifting term is calculated by making use of previously computed ones as well as the positive samples and the output of the model. %One key step is to properly scale the drifting terms so that their magnitudes are in a comparable range. In principle, the drifting terms obtained at a later stage capture higher order gradient information towards the positive samples. At each training iteration, the model is optimized by pushing its output towards the direction of the (weighted) summation of the drifting terms. Experimental results on toy examples and CIFAR10 demonstrate the better performance of the new method than the baseline.
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。