论文标题
超越了分类中的一热编码：人类不确定性可以改善模型性能吗？
Going Beyond One-Hot Encoding in Classification: Can Human Uncertainty Improve Model Performance?
论文作者
论文摘要
技术和计算进步不断推动深度学习的广泛领域。近年来，描述预测中确定性的数量的推导（自然伴随着建模过程）引发了人们对深度学习社区的普遍兴趣。在机器学习环境中通常被忽略的是影响众多标签过程的人类不确定性。作为这项工作的核心，标签不确定性通过分配标签明确嵌入了训练过程中。我们使用遥感数据集展示了方法对图像分类的有效性，该数据集包含域专家的多个标签投票，每张图像：标签不确定性的结合有助于该模型更好地推广到不看到数据并提高模型性能。与现有的校准方法相似，分布标签会导致更好地校准的概率，从而产生更确定和值得信赖的预测。
Technological and computational advances continuously drive forward the broad field of deep learning. In recent years, the derivation of quantities describing theuncertainty in the prediction - which naturally accompanies the modeling process - has sparked general interest in the deep learning community. Often neglected in the machine learning setting is the human uncertainty that influences numerous labeling processes. As the core of this work, label uncertainty is explicitly embedded into the training process via distributional labels. We demonstrate the effectiveness of our approach on image classification with a remote sensing data set that contains multiple label votes by domain experts for each image: The incorporation of label uncertainty helps the model to generalize better to unseen data and increases model performance. Similar to existing calibration methods, the distributional labels lead to better-calibrated probabilities, which in turn yield more certain and trustworthy predictions.
