FocusDiT: 扩散Transformer中的查询掩码用于细粒度图像生成
FocusDiT: Masking Queries in Diffusion Transformers for Fine-grained Image Generation
AI总结：
提出FocusDiT方法，通过掩码关键查询令牌仅输入FFN层，增强细粒度视觉生成，实验验证其有效性。
摘要：
扩散Transformer（DiT）已被广泛应用于生成扩散领域，通过注意力和前馈（FFN）层推进查询令牌的去噪。FFN实际上充当解码视觉内容的键值词汇表，其中值嵌入视觉语义知识。我们提出，关注对应于更复杂细节的关键查询令牌，并鼓励模型改进这些令牌，对于细粒度视觉生成至关重要。为此，我们提出FocusDiT，它应用掩码方案来关注仅输入FFN的关键查询令牌。掩码查询可以从FFN词汇表中检索视觉令牌，并使用它们解码其视觉细节。大量的文本到图像实验验证了令牌掩码在增强生成性能方面的有效性。
英文摘要：
Diffusion transformer (DiT) has been widely adopted in the generative diffusion field, advancing the denoising of query tokens through attention and Feed-Forward (\text{FFN}) layers. FFN actually acts as the key-value vocabulary for decoding visual contents where the value embeds the visual semantical knowledge. We present that focusing on critical query tokens corresponding to more complex details and encouraging the model to improve these tokens is essential for fine-grained visual generation. To this end, we propose FocusDiT, which applies a Masking scheme to focus on critical query tokens that are exclusively fed into FFN. The masked queries can retrieve visual tokens from the FFN vocabularies, and use them to decode their visual details. Extensive text-to-image experiments validate the effectiveness of token masking in enhancing generative performance.
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。
