论文标题
老虎：通过交替最小化，深度神经网络和软标签的共同学习
COLAM: Co-Learning of Deep Neural Networks and Soft Labels via Alternating Minimization
论文作者
论文摘要
相对于数据表示的训练数据集的软化标签经常用于改善深神经网络（DNNS）的训练。虽然已经研究了这种做法是一种利用有关数据分布的特权信息的一种方式，但训练有素的具有软分类输出的学习者应首先作为生成此类特权信息之前作为一种获得。为了解决此类鸡肉蛋的问题，我们提出了Colam框架，通过交替地最小化两个目标 - （a）在一个端到端的训练程序中学习改进的软标签的目标，以最大程度地限制两个目标，以交替地将训练损失与柔软的标签进行交替。我们进行了广泛的实验，以将我们提出的方法与一系列基线进行比较。实验结果表明，Colam具有更好的测试分类准确性，在许多任务上的性能提高了。我们还提供定性和定量分析，这些分析解释了Colam为什么效果很好。
Softening labels of training datasets with respect to data representations has been frequently used to improve the training of deep neural networks (DNNs). While such a practice has been studied as a way to leverage privileged information about the distribution of the data, a well-trained learner with soft classification outputs should be first obtained as a prior to generate such privileged information. To solve such chicken-egg problem, we propose COLAM framework that Co-Learns DNNs and soft labels through Alternating Minimization of two objectives - (a) the training loss subject to soft labels and (b) the objective to learn improved soft labels - in one end-to-end training procedure. We performed extensive experiments to compare our proposed method with a series of baselines. The experiment results show that COLAM achieves improved performance on many tasks with better testing classification accuracy. We also provide both qualitative and quantitative analyses that explain why COLAM works well.
