When incrementally trained on new classes, deep neural networks are subject to catastrophic forgetting which leads to an extreme deterioration of their performance on the old classes while learning the new ones. Using a small memory containing few samples from past classes has shown to be an effective method to mitigate catastrophic forgetting. However, due to the limited size of the replay memory, there is a large imbalance between the number of samples for the new and the old classes in the training dataset resulting in bias in the final model. To address this issue, we propose to use the Balanced Softmax Cross-Entropy and show that it can be seamlessly combined with state-of-the-art approaches for class-incremental learning in order to improve their accuracy while also potentially decreasing the computational cost of the training procedure. We further extend this approach to the more demanding class-incremental learning without memory setting and achieve competitive results with memory-based approaches. Experiments on the challenging ImageNet, ImageNet-Subset and CIFAR100 benchmarks with various settings demonstrate the benefits of our approach.
翻译:深神经网络在新班级逐步培训时,会被灾难性地遗忘,导致旧班级的成绩在学习新班级的同时急剧恶化。使用包含过去班级少数样本的小型记忆显示,这是减轻灾难性记忆的有效方法。然而,由于回放记忆的大小有限,培训数据集中新班和旧班的样品数量之间有很大的不平衡,导致最后模型的偏差。为了解决这一问题,我们提议使用平衡软体跨气流,并表明它可以与最新的课堂学习方法无缝结合,以提高其准确性,同时可能降低培训程序的计算成本。我们进一步将这一方法扩大到更苛刻的课堂学习,而不设置记忆,以记忆为基础的方法取得竞争性结果。对具有挑战性的图像网络、图像网络子集和CIFAR100基准的实验,以各种环境展示了我们方法的效益。