论文标题
利用功能和分类器之间的角度信息进行长尾学习：一种预测重新制定方法
Leveraging Angular Information Between Feature and Classifier for Long-tailed Learning: A Prediction Reformulation Approach
论文作者
论文摘要
深层神经网络仍在长尾图像数据集上挣扎，原因之一是跨类别的训练数据的不平衡导致训练有素的模型参数的不平衡。受训练的分类器在元素阶层中产生更大的体重规范的经验发现的动机，我们建议通过随附的角度重新重新识别识别概率，而无需重新平衡分类器的权重。具体而言，我们计算数据特征和类别分类器权重之间的角度以获得基于角度的预测结果。受到预测形式重新印象的性能改善以及广泛使用的两阶段学习框架的出色性能的启发，我们探索了该角度预测的不同属性，并提出了新型模块，以提高框架中不同组件的性能。我们的方法能够在同行方法中获得最佳性能，而无需在CIFAR10/100-LT和Imagenet-LT上进行预读。源代码将公开可用。
Deep neural networks still struggle on long-tailed image datasets, and one of the reasons is that the imbalance of training data across categories leads to the imbalance of trained model parameters. Motivated by the empirical findings that trained classifiers yield larger weight norms in head classes, we propose to reformulate the recognition probabilities through included angles without re-balancing the classifier weights. Specifically, we calculate the angles between the data feature and the class-wise classifier weights to obtain angle-based prediction results. Inspired by the performance improvement of the predictive form reformulation and the outstanding performance of the widely used two-stage learning framework, we explore the different properties of this angular prediction and propose novel modules to improve the performance of different components in the framework. Our method is able to obtain the best performance among peer methods without pretraining on CIFAR10/100-LT and ImageNet-LT. Source code will be made publicly available.
