Normalizing Batch Normalization for Long-Tailed Recognition
This addresses performance degradation on rare classes in imbalanced datasets, which is a common issue in real-world applications, but the approach is incremental as it builds on existing Batch Normalization techniques.
The paper tackles the problem of long-tailed recognition in neural networks by identifying that feature bias towards frequent classes weakens rare-specific features, and introduces a method to normalize Batch Normalization parameters to rectify this bias, achieving state-of-the-art performance on benchmarks like CIFAR-10/100-LT, ImageNet-LT, and iNaturalist 2018.
In real-world scenarios, the number of training samples across classes usually subjects to a long-tailed distribution. The conventionally trained network may achieve unexpected inferior performance on the rare class compared to the frequent class. Most previous works attempt to rectify the network bias from the data-level or from the classifier-level. Differently, in this paper, we identify that the bias towards the frequent class may be encoded into features, i.e., the rare-specific features which play a key role in discriminating the rare class are much weaker than the frequent-specific features. Based on such an observation, we introduce a simple yet effective approach, normalizing the parameters of Batch Normalization (BN) layer to explicitly rectify the feature bias. To achieve this end, we represent the Weight/Bias parameters of a BN layer as a vector, normalize it into a unit one and multiply the unit vector by a scalar learnable parameter. Through decoupling the direction and magnitude of parameters in BN layer to learn, the Weight/Bias exhibits a more balanced distribution and thus the strength of features becomes more even. Extensive experiments on various long-tailed recognition benchmarks (i.e., CIFAR-10/100-LT, ImageNet-LT and iNaturalist 2018) show that our method outperforms previous state-of-the-arts remarkably. The code and checkpoints are available at https://github.com/yuxiangbao/NBN.