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: this https URL

通过引入新的不对称损失 (ASL) 并对正负样本进行不同的操作，实现了动态减小容易的负样本，并去除可能被错误标记的样本，使得多标签数据集像 MS-COCO、Pascal-VOC、NUS-WIDE 和 Open Images 的 mAP 得分更加平衡，达到了最新的表现水平，同时也展示了 ASL 适用于其他任务，如单标签分类和物体检测。