Asperti Andrea, Fiorilla Salvatore, Orsini Lorenzo
Department of Informatics-Science and Engineering (DISI), University of Bologna, 40126 Bologna, Italy.
Sensors (Basel). 2024 Feb 15;24(4):1240. doi: 10.3390/s24041240.
Person Re-identification is the task of recognizing comparable subjects across a network of nonoverlapping cameras. This is typically achieved by extracting from the source image a vector of characteristic features of the specific person captured by the camera. Learning a good set of robust, invariant and discriminative features is a complex task, often leveraging contrastive learning. In this article, we explore a different approach, learning the representation of an individual as the conditioning information required to generate images of the specific person starting from random noise. In this way we decouple the identity of the individual from any other information relative to a specific instance (pose, background, etc.), allowing interesting transformations from one identity to another. As generative models, we use the recent diffusion models that have already proven their sensibility to conditioning in many different contexts. The results presented in this article serve as a proof-of-concept. While our current performance on common benchmarks is lower than state-of-the-art techniques, the approach is intriguing and rich of innovative insights, suggesting a wide range of potential improvements along various lines of investigation.
人物重新识别是指在由不重叠摄像头组成的网络中识别可比较主体的任务。这通常是通过从源图像中提取摄像头捕捉到的特定人物的特征向量来实现的。学习一组良好的鲁棒、不变且有区分性的特征是一项复杂的任务，通常需要利用对比学习。在本文中，我们探索了一种不同的方法，即将个体的表征学习为从随机噪声开始生成特定人物图像所需的条件信息。通过这种方式，我们将个体的身份与相对于特定实例的任何其他信息（姿势、背景等）解耦，从而实现从一个身份到另一个身份的有趣变换。作为生成模型，我们使用了最近的扩散模型，这些模型在许多不同的场景中已经证明了它们对条件的敏感性。本文展示的结果作为一种概念验证。虽然我们目前在常见基准测试中的性能低于当前的先进技术，但该方法很有趣且富有创新见解，表明沿着各种研究方向有广泛的潜在改进空间。
