arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2105.04522cs.LGcs.CVstat.ML
收藏

带噪声标签学习的广义Jensen-Shannon发散损失

Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels

KTH(瑞典皇家理工学院)

Erik Englesson, Hossein Azizpour

摘要:

先前的工作已经发现,将可证明的噪声鲁棒损失函数,具有标准分类损失函数的平均绝对误差(MAE),例如交叉熵(CE),以提高其可学习性。在这里,我们建议使用Jensen-Shannon分歧作为噪声鲁棒性损失函数,并表明它有趣地在CE和MAE之间插值,并具有可控的混合参数。此外,我们做了一个重要的观察,CE表现出较低的一致性周围的噪声数据点。基于这一观察结果,我们采用了广义版本的詹森-香农分歧的多个分布,以鼓励数据点周围的一致性。使用这个损失函数,我们展示了合成(CIFAR)和真实世界(例如,WebVision)噪声,具有不同的噪声率。

英文摘要:

Prior works have found it beneficial to combine provably noise-robust loss functions e.g., mean absolute error (MAE) with standard categorical loss function e.g. cross entropy (CE) to improve their learnability. Here, we propose to use Jensen-Shannon divergence as a noise-robust loss function and show that it interestingly interpolate between CE and MAE with a controllable mixing parameter. Furthermore, we make a crucial observation that CE exhibit lower consistency around noisy data points. Based on this observation, we adopt a generalized version of the Jensen-Shannon divergence for multiple distributions to encourage consistency around data points. Using this loss function, we show state-of-the-art results on both synthetic (CIFAR), and real-world (e.g., WebVision) noise with varying noise rates.

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。

↑