ReGround：在不增加成本的情况下改进文本与空间定位
ReGround: Improving Textual and Spatial Grounding at No Cost
AI总结：
本文提出ReGround，通过将门控自注意力与交叉注意力从顺序改为并行，无需微调即可缓解扩散模型中空间定位对文本定位的压制，显著改善两者权衡。
摘要：
当图像生成过程同时由文本提示和空间线索（如一组边界框）引导时，这些元素是协同工作，还是其中一个主导另一个？我们对一个将门控自注意力集成到U-Net中的预训练图像扩散模型的分析表明，由于门控自注意力到交叉注意力的顺序流动，空间定位往往超过文本定位。我们证明，通过简单地重新连接网络架构，将门控自注意力和交叉注意力从顺序改为并行，可以在不牺牲任一接地精度的情况下显著缓解这种偏差。这一出奇简单且有效的解决方案不需要对网络进行任何微调，但显著减少了两种接地之间的权衡。我们的实验表明，从原始GLIGEN到重新连接版本，在文本定位和空间定位之间的权衡方面有显著改进。
英文摘要：
When an image generation process is guided by both a text prompt and spatial cues, such as a set of bounding boxes, do these elements work in harmony, or does one dominate the other? Our analysis of a pretrained image diffusion model that integrates gated self-attention into the U-Net reveals that spatial grounding often outweighs textual grounding due to the sequential flow from gated self-attention to cross-attention. We demonstrate that such bias can be significantly mitigated without sacrificing accuracy in either grounding by simply rewiring the network architecture, changing from sequential to parallel for gated self-attention and cross-attention. This surprisingly simple yet effective solution does not require any fine-tuning of the network but significantly reduces the trade-off between the two groundings. Our experiments demonstrate significant improvements from the original GLIGEN to the rewired version in the trade-off between textual grounding and spatial grounding.
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。
