Wu Ancong, Ge Wenhang, Zheng Wei-Shi
IEEE Trans Pattern Anal Mach Intell. 2023 Dec;45(12):15512-15529. doi: 10.1109/TPAMI.2023.3292936. Epub 2023 Nov 3.
Semi-supervised person re-identification (Re-ID) is an important approach for alleviating annotation costs when learning to match person images across camera views. Most existing works assume that training data contains abundant identities crossing camera views. However, this assumption is not true in many real-world applications, especially when images are captured in nonadjacent scenes for Re-ID in wider areas, where the identities rarely cross camera views. In this work, we operate semi-supervised Re-ID under a relaxed assumption of identities rarely crossing camera views, which is still largely ignored in existing methods. Since the identities rarely cross camera views, the underlying sample relations across camera views become much more uncertain, and deteriorate the noise accumulation problem in many advanced Re-ID methods that apply pseudo labeling for associating visually similar samples. To quantify such uncertainty, we parameterize the probabilistic relations between samples in a relation discovery objective for pseudo label training. Then, we introduce reward quantified by identification performance on a few labeled data to guide learning dynamic relations between samples for reducing uncertainty. Our strategy is called the Rewarded Relation Discovery (R D), of which the rewarded learning paradigm is under-explored in existing pseudo labeling methods. To further reduce the uncertainty in sample relations, we perform multiple relation discovery objectives learning to discover probabilistic relations based on different prior knowledge of intra-camera affinity and cross-camera style variation, and fuse the complementary knowledge of different probabilistic relations by similarity distillation. To better evaluate semi-supervised Re-ID on identities rarely crossing camera views, we collect a new real-world dataset called REID-CBD, and perform simulation on benchmark datasets. Experiment results show that our method outperforms a wide range of semi-supervised and unsupervised learning methods.
半监督行人重识别（Re-ID）是一种在跨摄像头视图学习匹配行人图像时减轻标注成本的重要方法。大多数现有工作都假设训练数据包含大量跨摄像头视图的身份。然而，在许多实际应用中，这一假设并不成立，尤其是当在更广泛区域进行Re-ID的非相邻场景中捕获图像时，身份很少会跨摄像头视图。在这项工作中，我们在身份很少跨摄像头视图的宽松假设下进行半监督Re-ID，而这在现有方法中仍 largely被忽略。由于身份很少跨摄像头视图，跨摄像头视图的潜在样本关系变得更加不确定，并在许多应用伪标签来关联视觉相似样本的先进Re-ID方法中加剧了噪声积累问题。为了量化这种不确定性，我们在用于伪标签训练的关系发现目标中对样本之间的概率关系进行参数化。然后，我们引入通过对少量标注数据的识别性能量化的奖励，以指导学习样本之间的动态关系以减少不确定性。我们的策略称为奖励关系发现（RD），其奖励学习范式在现有伪标签方法中尚未得到充分探索。为了进一步降低样本关系中的不确定性，我们执行多个关系发现目标学习，以基于关于摄像头内亲和力和跨摄像头风格变化的不同先验知识发现概率关系，并通过相似性蒸馏融合不同概率关系的互补知识。为了更好地评估在身份很少跨摄像头视图情况下的半监督Re-ID，我们收集了一个名为REID-CBD的新真实世界数据集，并在基准数据集上进行了模拟。实验结果表明，我们的方法优于广泛的半监督和无监督学习方法。
