It is well-known that a deep neural network has a strong fitting capability and can easily achieve a low training error even with randomly assigned class labels. When the number of training samples is small, or the class labels are noisy, networks tend to memorize patterns specific to individual instances to minimize the training error. This leads to the issue of overfitting and poor generalisation performance. This paper explores a remedy by suppressing the network's tendency to rely on instance-specific patterns for empirical error minimisation. The proposed method is based on an adversarial training framework. It suppresses features that can be utilized to identify individual instances among samples within each class. This leads to classifiers only using features that are both discriminative across classes and common within each class. We call our method Adversarial Suppression of Identity Features (ASIF), and demonstrate the usefulness of this technique in boosting generalisation accuracy when faced with small datasets or noisy labels. Our source code is available.
翻译:众所周知,深层神经网络具有很强的安装能力,即使随机分配类标签,也可以很容易地实现低培训错误。当培训样本数量少或类标签吵闹时,网络往往会记住个别实例特有的模式,以尽量减少培训错误。这导致了超配和概括性表现差的问题。本文探讨了一种补救措施,抑制了网络依赖具体实例模式来减少经验错误的趋势。拟议方法以对抗性培训框架为基础。它抑制了可用于识别每类样本中个别案例的特征。这导致分类者只使用不同类别和每个类别中常见的特征。我们称之为我们的方法“限制身份特征特征特征”(ASIF),并展示了这种技术在面对小数据集或杂音标签时在提高通用准确性方面的有用性。我们的源代码是可用的。