arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.02454cs.CVcs.LG
收藏

自适应提高跨领域泛化能力

Self-Challenging Improves Cross-Domain Generalization

Carnegie Mellon University(卡内基梅隆大学)

Zeyi Huang, Haohan Wang, Eric P. Xing, Dong Huang

摘要:

卷积神经网络(CNN)通过激活与标签相关的主导特征来进行图像分类。当训练数据和测试数据处于相似的分布下时,它们的主要特征是相似的,这通常有助于在测试数据上表现出良好的性能。然而,当对来自不同分布的样本进行测试时,性能未得到满足,从而导致跨域图像分类的挑战。我们引入了一个简单的训练启发式,表示自适应(RSC),显着提高了CNN到域外数据的泛化。RSC迭代地挑战(丢弃)在训练数据上激活的主要特征,并迫使网络激活与标签相关的剩余特征。这个过程似乎激活适用于域外数据的特征表示,而无需事先了解新的域,也无需学习额外的网络参数。本文给出了改进跨领域泛化的RSC的理论性质和条件。实验结果表明,我们的RSC方法简单,有效和架构不可知的性质。

英文摘要:

Convolutional Neural Networks (CNN) conduct image classification by activating dominant features that correlated with labels. When the training and testing data are under similar distributions, their dominant features are similar, which usually facilitates decent performance on the testing data. The performance is nonetheless unmet when tested on samples from different distributions, leading to the challenges in cross-domain image classification. We introduce a simple training heuristic, Representation Self-Challenging (RSC), that significantly improves the generalization of CNN to the out-of-domain data. RSC iteratively challenges (discards) the dominant features activated on the training data, and forces the network to activate remaining features that correlates with labels. This process appears to activate feature representations applicable to out-of-domain data without prior knowledge of new domain and without learning extra network parameters. We present theoretical properties and conditions of RSC for improving cross-domain generalization. The experiments endorse the simple, effective and architecture-agnostic nature of our RSC method.

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。

↑