论文标题
识别和补偿不平衡的深度学习中的特征偏差
Identifying and Compensating for Feature Deviation in Imbalanced Deep Learning
论文作者
论文摘要
已知经过类不平衡数据的分类器在“次要”类的测试数据上表现不佳，我们的培训数据不足。在本文中，我们调查在这种情况下学习Convnet分类器。我们发现，Convnet显着夸大了次要类别，这与通常不足的次要类别的传统机器学习算法完全相反。我们进行了一系列分析，并发现了特征偏差现象 - 学识渊博的Convnet在次要类别的训练和测试数据之间产生偏差的特征 - 这解释了过度拟合的情况。为了补偿特征偏差的效果，将测试数据推向低决策价值区域，我们建议将依赖类的温度（CDT）纳入训练convnet。 CDT模拟了训练阶段的特征偏差，迫使Convnet扩大次级数据的决策值，从而可以在测试阶段克服实际特征偏差。我们在基准数据集上验证我们的方法并实现有希望的性能。我们希望我们的见解能够激发解决班级失去平衡深度学习的新思维方式。
Classifiers trained with class-imbalanced data are known to perform poorly on test data of the "minor" classes, of which we have insufficient training data. In this paper, we investigate learning a ConvNet classifier under such a scenario. We found that a ConvNet significantly over-fits the minor classes, which is quite opposite to traditional machine learning algorithms that often under-fit minor classes. We conducted a series of analysis and discovered the feature deviation phenomenon -- the learned ConvNet generates deviated features between the training and test data of minor classes -- which explains how over-fitting happens. To compensate for the effect of feature deviation which pushes test data toward low decision value regions, we propose to incorporate class-dependent temperatures (CDT) in training a ConvNet. CDT simulates feature deviation in the training phase, forcing the ConvNet to enlarge the decision values for minor-class data so that it can overcome real feature deviation in the test phase. We validate our approach on benchmark datasets and achieve promising performance. We hope that our insights can inspire new ways of thinking in resolving class-imbalanced deep learning.
