论文标题
多标签分类的不对称损失
Asymmetric Loss For Multi-Label Classification
论文作者
论文摘要
在典型的多标签设置中，图片平均包含很少的正标和许多负标签。这种阳性阴性的失衡主导了优化过程，并可能导致训练过程中正面标签的梯度不足，从而导致准确性差。在本文中，我们引入了一种新型的不对称损失（“ ASL”），该损失在正面和负样本上有所不同。损失使动态下降和硬阈值易于负面样本，同时还可以丢弃可能错误的样本。我们演示了ASL如何平衡不同样本的概率，以及如何将这种平衡转化为更好的地图分数。使用ASL，我们可以在多个流行的多标签数据集上达到最新结果：MS-Coco，Pascal-Voc，Nus Wide和Open Images。我们还展示了针对其他任务的ASL适用性，例如单标签分类和对象检测。 ASL有效，易于实施，不会增加训练时间或复杂性。 实施可在以下网址获得：https：//github.com/alibaba-miil/asl。
In a typical multi-label setting, a picture contains on average few positive labels, and many negative ones. This positive-negative imbalance dominates the optimization process, and can lead to under-emphasizing gradients from positive labels during training, resulting in poor accuracy. In this paper, we introduce a novel asymmetric loss ("ASL"), which operates differently on positive and negative samples. The loss enables to dynamically down-weights and hard-thresholds easy negative samples, while also discarding possibly mislabeled samples. We demonstrate how ASL can balance the probabilities of different samples, and how this balancing is translated to better mAP scores. With ASL, we reach state-of-the-art results on multiple popular multi-label datasets: MS-COCO, Pascal-VOC, NUS-WIDE and Open Images. We also demonstrate ASL applicability for other tasks, such as single-label classification and object detection. ASL is effective, easy to implement, and does not increase the training time or complexity. Implementation is available at: https://github.com/Alibaba-MIIL/ASL.
