In this paper, we propose a patch-based architecture for multi-label classification problems where only a single positive label is observed in images of the dataset. Our contributions are twofold. First, we introduce a light patch architecture based on the attention mechanism. Next, leveraging on patch embedding self-similarities, we provide a novel strategy for estimating negative examples and deal with positive and unlabeled learning problems. Experiments demonstrate that our architecture can be trained from scratch, whereas pre-training on similar databases is required for related methods from the literature.

翻译：在本文中,我们建议为多标签分类问题建立一个基于补丁的架构,在这种架构中,数据集的图像中只看到一个单一的正面标签。我们的贡献是双重的。首先,我们引入了一个基于关注机制的光补丁架构。接着,利用补丁嵌入自我差异,我们提供了一个新的策略来估计负面实例,并处理正面和无标签的学习问题。实验表明,我们的架构可以从零开始就接受培训,而类似的数据库则需要预先培训,以便从文献中找到相关方法。