不要错过不匹配：无监督表示学习的目标函数不匹配研究
Don't miss the Mismatch: Investigating the Objective Function Mismatch for Unsupervised Representation Learning
摘要：
为无监督表示学习技术寻找通用的评价指标是一个具有挑战性的开放研究问题，由于对无监督方法的兴趣日益增加，这一问题变得越来越必要。尽管这些方法承诺有益的表示特性，但目前大多数方法都存在目标函数不匹配的问题。这种不匹配表明，当无监督的借口任务学习时间过长时，所需目标任务的性能可能会下降-特别是当两个任务都是不适定时。在这项工作中，我们建立在广泛使用的线性评估协议，并定义新的一般评估指标，以定量地捕捉目标函数不匹配和更通用的指标不匹配。我们讨论了我们的协议的可用性和稳定性的各种借口和目标任务，并在广泛的实验研究不匹配。因此，我们披露的依赖关系的目标函数不匹配的几个借口和目标任务的借口模型的表示大小，目标模型的复杂性，借口和目标增强，以及借口和目标任务类型。在我们的实验中，我们发现目标函数不匹配在许多设置中会使Cifar 10，Cifar 100和PCam的性能降低约0.1-5.0%，在极端情况下，3dshapes数据集的性能降低约25-59%。
英文摘要：
Finding general evaluation metrics for unsupervised representation learning techniques is a challenging open research question, which recently has become more and more necessary due to the increasing interest in unsupervised methods. Even though these methods promise beneficial representation characteristics, most approaches currently suffer from the objective function mismatch. This mismatch states that the performance on a desired target task can decrease when the unsupervised pretext task is learned too long - especially when both tasks are ill-posed. In this work, we build upon the widely used linear evaluation protocol and define new general evaluation metrics to quantitatively capture the objective function mismatch and the more generic metrics mismatch. We discuss the usability and stability of our protocols on a variety of pretext and target tasks and study mismatches in a wide range of experiments. Thereby we disclose dependencies of the objective function mismatch across several pretext and target tasks with respect to the pretext model's representation size, target model complexity, pretext and target augmentations as well as pretext and target task types. In our experiments, we find that the objective function mismatch reduces performance by ~0.1-5.0% for Cifar10, Cifar100 and PCam in many setups, and up to ~25-59% in extreme cases for the 3dshapes dataset.
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。
