arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1701.03077cs.CVcs.LGstat.ML
收藏

一种通用的自适应鲁棒损失函数

A General and Adaptive Robust Loss Function

Google Research(谷歌研究院)

Jonathan T. Barron

摘要:

我们给出了Cauchy/Lorentzian、Geman-McClure、Welsch/Leclerc、广义Charbonnier、Charbonnier/pseudo-Huber/L1-L2和L2损失函数的推广。通过引入鲁棒性作为连续参数,我们的损失函数允许围绕鲁棒损失最小化构建的算法被推广,这提高了基本视觉任务(如配准和聚类)的性能。将我们的损失解释为单变量密度的负对数,会产生一个一般概率分布,其中包括正态分布和柯西分布作为特殊情况。这种概率解释使得能够训练神经网络,其中损失的鲁棒性在训练期间自动自适应,这提高了基于学习的任务(例如生成图像合成和无监督单目深度估计)的性能,而不需要任何手动参数调整。

英文摘要:

We present a generalization of the Cauchy/Lorentzian, Geman-McClure, Welsch/Leclerc, generalized Charbonnier, Charbonnier/pseudo-Huber/L1-L2, and L2 loss functions. By introducing robustness as a continuous parameter, our loss function allows algorithms built around robust loss minimization to be generalized, which improves performance on basic vision tasks such as registration and clustering. Interpreting our loss as the negative log of a univariate density yields a general probability distribution that includes normal and Cauchy distributions as special cases. This probabilistic interpretation enables the training of neural networks in which the robustness of the loss automatically adapts itself during training, which improves performance on learning-based tasks such as generative image synthesis and unsupervised monocular depth estimation, without requiring any manual parameter tuning.

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。

↑