In real-world scenarios, collected and annotated data often exhibit the characteristics of multiple classes and long-tailed distribution. Additionally, label noise is inevitable in large-scale annotations and hinders the applications of learning-based models. Although many deep learning based methods have been proposed for handling long-tailed multi-label recognition or label noise respectively, learning with noisy labels in long-tailed multi-label visual data has not been well-studied because of the complexity of long-tailed distribution entangled with multi-label correlation. To tackle such a critical yet thorny problem, this paper focuses on reducing noise based on some inherent properties of multi-label classification and long-tailed learning under noisy cases. In detail, we propose a Stitch-Up augmentation to synthesize a cleaner sample, which directly reduces multi-label noise by stitching up multiple noisy training samples. Equipped with Stitch-Up, a Heterogeneous Co-Learning framework is further designed to leverage the inconsistency between long-tailed and balanced distributions, yielding cleaner labels for more robust representation learning with noisy long-tailed data. To validate our method, we build two challenging benchmarks, named VOC-MLT-Noise and COCO-MLT-Noise, respectively. Extensive experiments are conducted to demonstrate the effectiveness of our proposed method. Compared to a variety of baselines, our method achieves superior results.

翻译：现实场景中，收集和标注的数据往往呈现多类别与长尾分布的特征。此外，大规模标注中标签噪声不可避免，阻碍了基于学习模型的应用。尽管已有许多深度学习方法分别处理长尾多标签识别或标签噪声问题，但在长尾多标签视觉数据中学习带噪标签的研究仍不充分，原因在于长尾分布与多标签关联性交织的复杂性。为攻克这一关键难题，本文聚焦于利用多标签分类与长尾学习在噪声场景下的固有特性来降低噪声。具体而言，我们提出一种"缝合增强"（Stitch-Up）方法，通过拼接多个含噪训练样本直接合成更干净的样本，从而减轻多标签噪声。结合Stitch-Up，我们进一步设计了异质协同学习框架（Heterogeneous Co-Learning），利用长尾分布与平衡分布之间的不一致性，为含噪长尾数据生成更干净的标签，以实现更鲁棒的表示学习。为验证方法有效性，我们构建了两个具有挑战性的基准数据集VOC-MLT-Noise和COCO-MLT-Noise。大量实验证明，所提方法相较多种基线取得了更优结果。