论文标题
Simloss：交叉熵的类相似性
SimLoss: Class Similarities in Cross Entropy
论文作者
论文摘要
神经网络分类任务中的一个常见损失函数是分类跨熵（CCE），它平均惩罚所有错误分类。但是，类通常具有固有的结构。例如，将玫瑰的图像归类为“紫罗兰色”胜于“卡车”。我们介绍了Simloss，这是CCE的一个替代品，它结合了类相似性以及两种技术，可以从特定于任务的知识中构造此类矩阵。我们测试了Simloss对年龄估计和图像分类的测试，并发现它对几个指标的CCE进行了重大改进。因此，Simloss可以通过简单地交换损失功能，同时保持神经网络体系结构相同，从而明确建模背景知识。可以在https://github.com/konstantinkobs/simloss上找到代码和其他资源。
One common loss function in neural network classification tasks is Categorical Cross Entropy (CCE), which punishes all misclassifications equally. However, classes often have an inherent structure. For instance, classifying an image of a rose as "violet" is better than as "truck". We introduce SimLoss, a drop-in replacement for CCE that incorporates class similarities along with two techniques to construct such matrices from task-specific knowledge. We test SimLoss on Age Estimation and Image Classification and find that it brings significant improvements over CCE on several metrics. SimLoss therefore allows for explicit modeling of background knowledge by simply exchanging the loss function, while keeping the neural network architecture the same. Code and additional resources can be found at https://github.com/konstantinkobs/SimLoss.
