arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2312.01367cs.CVcs.AI
收藏

DiFace:通过受控扩散实现跨模态人脸识别

DiFace: Cross-Modal Face Recognition through Controlled Diffusion

Shanghai Jiao Tong University(上海交通大学)

Bowen Sun, Shibao Zheng

AI总结:

本文提出DiFace,通过可控扩散过程建立与概率传输的理论联系,首次有效实现基于文本描述的人脸识别,并显著提升文本到图像人脸验证与辨识的准确率。

摘要:

扩散概率模型(DPMs)在生成高质量、高真实感的视觉媒体方面展现出卓越能力。然而,其在人脸识别等非生成领域中的潜力尚未得到充分探索。与此同时,尽管多模态人脸识别方法已得到广泛发展,但其重点主要集中在视觉模态上。在此背景下,通过文本描述进行人脸识别提供了一种独特且有前景的解决方案,不仅突破了应用场景的限制,也拓展了跨模态人脸识别领域的研究潜力。遗憾的是,这一方向仍未得到探索和充分利用,其原因主要来自三个方面的挑战:1)语言描述固有的不精确性;2)文本与图像之间存在显著差距;3)数据库不足所带来的巨大障碍。为解决这一问题,我们提出了DiFace,该方法通过建立与概率传输的理论联系,利用可控扩散过程有效实现基于文本的人脸识别。我们的方法不仅释放了DPMs在更广泛任务中的潜力,而且据我们所知,首次在文本到图像人脸识别中取得了显著准确率,验证与辨识实验证明了这一点。

英文摘要:

Diffusion probabilistic models (DPMs) have exhibited exceptional proficiency in generating visual media of outstanding quality and realism. Nonetheless, their potential in non-generative domains, such as face recognition, has yet to be thoroughly investigated. Meanwhile, despite the extensive development of multi-modal face recognition methods, their emphasis has predominantly centered on visual modalities. In this context, face recognition through textual description presents a unique and promising solution that not only transcends the limitations from application scenarios but also expands the potential for research in the field of cross-modal face recognition. It is regrettable that this avenue remains unexplored and underutilized, a consequence from the challenges mainly associated with three aspects: 1) the intrinsic imprecision of verbal descriptions; 2) the significant gaps between texts and images; and 3) the immense hurdle posed by insufficient databases.To tackle this problem, we present DiFace, a solution that effectively achieves face recognition via text through a controllable diffusion process, by establishing its theoretical connection with probability transport. Our approach not only unleashes the potential of DPMs across a broader spectrum of tasks but also achieves, to the best of our knowledge, a significant accuracy in text-to-image face recognition for the first time, as demonstrated by our experiments on verification and identification.

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。

↑