AdaGen: 为图像合成学习自适应策略
AdaGen: Learning Adaptive Policy for Image Synthesis
AI总结：
AdaGen通过学习自适应策略提升图像合成性能，采用强化学习优化调度过程，实现更高效的生成效果和可控的保真度-多样性权衡。
摘要：
近年来，图像合成的进步得益于强大的生成模型，如Masked Generative Transformers（MaskGIT）、自回归模型、扩散模型和校正流模型。这些模型成功的主要原理是将合成分解为多个步骤。然而，这种分解引入了大量步骤特定的参数（例如每一步的噪声水平或温度）。现有方法通常依赖于手动设计的规则来管理这种复杂性，需要专家知识和试错。此外，这些静态调度缺乏灵活性，无法适应每个样本的独特特性，导致性能不佳。为了解决这个问题，我们提出了AdaGen，一种通用、可学习且样本自适应的框架，用于调度迭代生成过程。具体来说，我们将调度问题建模为马尔可夫决策过程，其中一个轻量级的策略网络根据当前生成状态确定合适的参数，并可通过强化学习进行训练。重要的是，我们证明简单的奖励设计，如FID或预训练奖励模型，可以被轻易破解，可能无法可靠地保证生成样本的质量或多样性。因此，我们提出了一种对抗性奖励设计来指导策略网络的训练。最后，我们引入了推理时的细化策略和可控的保真度-多样性权衡机制，以进一步提升AdaGen的性能和灵活性。在四个生成范式上的全面实验验证了AdaGen的优越性。例如，AdaGen在DiT-XL上以三倍更低的推理成本实现了更好的性能，并在计算开销极小的情况下将VAR的FID从1.92提高到1.59。
英文摘要：
Recent advances in image synthesis have been propelled by powerful generative models, such as Masked Generative Transformers (MaskGIT), autoregressive models, diffusion models, and rectified flow models. A common principle behind their success is the decomposition of synthesis into multiple steps. However, this introduces a proliferation of step-specific parameters (e.g., noise level or temperature at each step). Existing approaches typically rely on manually-designed rules to manage this complexity, demanding expert knowledge and trial-and-error. Furthermore, these static schedules lack the flexibility to adapt to the unique characteristics of each sample, yielding sub-optimal performance. To address this issue, we present AdaGen, a general, learnable, and sample-adaptive framework for scheduling the iterative generation process. Specifically, we formulate the scheduling problem as a Markov Decision Process, where a lightweight policy network determines suitable parameters given the current generation state, and can be trained through reinforcement learning. Importantly, we demonstrate that simple reward designs, such as FID or pre-trained reward models, can be easily hacked and may not reliably guarantee the desired quality or diversity of generated samples. Therefore, we propose an adversarial reward design to guide the training of the policy networks. Finally, we introduce an inference-time refinement strategy and a controllable fidelity-diversity trade-off mechanism to further enhance the performance and flexibility of AdaGen. Comprehensive experiments on four generative paradigms validate the superiority of AdaGen. For example, AdaGen achieves better performance on DiT-XL with 3 times lower inference cost and improves the FID of VAR from 1.92 to 1.59 with negligible computational overhead.
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。
