论文标题
对象实例的持续学习
Continual Learning of Object Instances
论文作者
论文摘要
我们建议连续实例学习 - 一种将持续学习概念应用于区分同一对象类别实例的任务的方法。我们特别关注汽车对象，并逐步学会通过公制学习区分汽车实例。我们通过评估当前技术来开始论文。确定在现有方法中很明显灾难性遗忘，然后我们提出了两种补救措施。首先，我们通过标准化的跨透镜将度量学习正规化。其次，我们通过合成数据传输来增强现有模型。我们在三个大规模数据集上进行的广泛实验，使用两种不同的持续学习方法的不同体系结构，表明归一化的跨透镜和合成转移会导致现有技术的遗忘更少。
We propose continual instance learning - a method that applies the concept of continual learning to the task of distinguishing instances of the same object category. We specifically focus on the car object, and incrementally learn to distinguish car instances from each other with metric learning. We begin our paper by evaluating current techniques. Establishing that catastrophic forgetting is evident in existing methods, we then propose two remedies. Firstly, we regularise metric learning via Normalised Cross-Entropy. Secondly, we augment existing models with synthetic data transfer. Our extensive experiments on three large-scale datasets, using two different architectures for five different continual learning methods, reveal that Normalised cross-entropy and synthetic transfer leads to less forgetting in existing techniques.
