This study focuses on a novel task in text-to-image (T2I) generation, namely action customization. The objective of this task is to learn the co-existing action from limited data and generalize it to unseen humans or even animals. Experimental results show that existing subject-driven customization methods fail to learn the representative characteristics of actions and struggle in decoupling actions from context features, including appearance. To overcome the preference for low-level features and the entanglement of high-level features, we propose an inversion-based method Action-Disentangled Identifier (ADI) to learn action-specific identifiers from the exemplar images. ADI first expands the semantic conditioning space by introducing layer-wise identifier tokens, thereby increasing the representational richness while distributing the inversion across different features. Then, to block the inversion of action-agnostic features, ADI extracts the gradient invariance from the constructed sample triples and masks the updates of irrelevant channels. To comprehensively evaluate the task, we present an ActionBench that includes a variety of actions, each accompanied by meticulously selected samples. Both quantitative and qualitative results show that our ADI outperforms existing baselines in action-customized T2I generation.

翻译：本研究聚焦于文本到图像生成中的一项新任务，即动作定制。该任务的目标是从有限数据中学习共现动作，并将其泛化至未见的人类甚至动物。实验结果表明，现有基于主体驱动的定制方法难以学习动作的代表性特征，且在将动作从上下文特征（包括外观）中解耦时面临困难。为克服对低层特征的偏好及高层特征纠缠的问题，我们提出一种基于逆方法的动作解耦标识符，用于从示例图像中学习动作特定标识符。该方法首先通过引入分层标识符标记扩展语义条件空间，从而在将逆过程分散到不同特征的同时增加表征丰富性。随后，为阻断与动作无关特征的逆过程，该方法从构建的样本三元组中提取梯度不变性，并屏蔽无关通道的更新。为全面评估该任务，我们提出一个包含多种动作的基准测试，每个动作均配有精心挑选的样本。定量与定性结果均表明，我们的方法在动作定制文本到图像生成中优于现有基线方法。