Person re-identification (re-ID) requires densely distributed cameras. In practice, the person of interest may not be captured by cameras and, therefore, needs to be retrieved using subjective information (e.g., sketches from witnesses). Previous research defines this case using the sketch as sketch re-identification (Sketch re-ID) and focuses on eliminating the domain gap. Actually, subjectivity is another significant challenge. We model and investigate it by posing a new dataset with multi-witness descriptions. It features two aspects. 1) Large-scale. It contains over 4,763 sketches and 32,668 photos, making it the largest Sketch re-ID dataset. 2) Multi-perspective and multi-style. Our dataset offers multiple sketches for each identity. Witnesses' subjective cognition provides multiple perspectives on the same individual, while different artists' drawing styles provide variation in sketch styles. We further have two novel designs to alleviate the challenge of subjectivity. 1) Fusing subjectivity. We propose a non-local (NL) fusion module that gathers sketches from different witnesses for the same identity. 2) Introducing objectivity. An AttrAlign module utilizes attributes as an implicit mask to align cross-domain features. To push forward the advance of Sketch re-ID, we set three benchmarks (large-scale, multi-style, cross-style). Extensive experiments demonstrate our leading performance in these benchmarks. Dataset and Codes are publicly available at: https://github.com/Lin-Kayla/subjectivity-sketch-reid
翻译:人物重识别(re-ID)需要密集分布的摄像头。在实际应用中,目标人物可能未被摄像头捕捉到,因此需要利用主观信息(例如目击者的素描)进行检索。以往研究将此情况定义为素描重识别(Sketch re-ID),并侧重于消除领域差异。实际上,主观性是另一个重大挑战。我们通过构建一个包含多目击者描述的新数据集来建模并研究这一问题。该数据集具有两方面特点:1)大规模性。它包含超过4,763张素描和32,668张照片,是目前最大的Sketch re-ID数据集。2)多视角与多风格性。我们的数据集中每个身份对应多张素描。目击者的主观认知提供了对同一人物的多视角观察,而不同画家的绘画风格则带来了素描风格的多样性。我们进一步提出两种新颖设计以缓解主观性挑战:1)融合主观性。我们提出一种非局部(NL)融合模块,用于聚合同一身份不同目击者的素描。2)引入客观性。AttrAlign模块利用属性作为隐式掩码来对齐跨域特征。为推动Sketch re-ID领域的发展,我们设置了三个基准测试(大规模、多风格、跨风格)。大量实验表明,我们在这些基准测试中取得了领先性能。数据集与代码已在https://github.com/Lin-Kayla/subjectivity-sketch-reid 公开。