解锁ImageNet的多对象特性：自动化大规模多标签标注
Unlocking ImageNet's Multi-Object Nature: Automated Large-Scale Multilabel Annotation
AI总结：
本文提出自动化方法将ImageNet训练集转换为多标签数据集，提升模型分类性能和下游任务转移能力。
摘要：
原始ImageNet基准测试强制单标签假设，尽管许多图像描绘多个对象。这导致标签噪声并限制了学习信号的丰富性。多标签标注更准确地反映了现实世界中的视觉场景，其中多个对象共存并促进语义理解，使模型能够学习更丰富和更稳健的表示。尽管先前的努力（例如ReaL、ImageNetv2）已改进验证集，但尚未有可扩展、高质量的多标签标注用于训练集。为此，我们提出一个自动化流程，将ImageNet训练集转换为多标签数据集，而无需人工标注。使用自监督视觉Transformer，我们执行无监督对象发现，选择与原始标签对齐的区域以训练一个轻量级分类器，并将其应用于所有区域以在数据集中生成连贯的多标签标注。我们的标签在定性评估中与人类判断有很强的对齐性，并在定量基准上持续提高性能。与传统单标签方案相比，使用我们多标签监督训练的模型在各种架构上实现了更准确的领域内准确性（在ReaL上最高+2.0 top-1准确率，在ImageNet-V2上+1.5）并表现出更强的下游任务转移能力（在COCO和VOC上分别最高+4.2和+2.3 mAP）。这些结果强调了准确多标签标注在提高分类性能和表示学习中的重要性。项目代码和生成的多标签标注可在https://github.com/jchen175/MultiLabel-ImageNet上获得。
英文摘要：
The original ImageNet benchmark enforces a single-label assumption, despite many images depicting multiple objects. This leads to label noise and limits the richness of the learning signal. Multi-label annotations more accurately reflect real-world visual scenes, where multiple objects co-occur and contribute to semantic understanding, enabling models to learn richer and more robust representations. While prior efforts (e.g., ReaL, ImageNetv2) have improved the validation set, there has not yet been a scalable, high-quality multi-label annotation for the training set. To this end, we present an automated pipeline to convert the ImageNet training set into a multi-label dataset, without human annotations. Using self-supervised Vision Transformers, we perform unsupervised object discovery, select regions aligned with original labels to train a lightweight classifier, and apply it to all regions to generate coherent multi-label annotations across the dataset. Our labels show strong alignment with human judgment in qualitative evaluations and consistently improve performance across quantitative benchmarks. Compared to traditional single-label scheme, models trained with our multi-label supervision achieve consistently better in-domain accuracy across architectures (up to +2.0 top-1 accuracy on ReaL and +1.5 on ImageNet-V2) and exhibit stronger transferability to downstream tasks (up to +4.2 and +2.3 mAP on COCO and VOC, respectively). These results underscore the importance of accurate multi-label annotations for enhancing both classification performance and representation learning. Project code and the generated multi-label annotations are available at https://github.com/jchen175/MultiLabel-ImageNet.
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。
