Confidence Estimation Using Unlabeled Data-猫眼课题宝

DOI：

10.48550/arxiv.2307.10440

发表时间：

2023-07

期刊：

ArXiv

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Chen Li;Xiaoling Hu;Chao Chen

过度自信是深度神经网络的一个常见问题，限制了它们在现实世界应用中的部署。为了更好地估计置信度，现有方法大多集中在完全监督的场景中，并依赖于训练标签。在本文中，我们提出了第一个半监督设置的置信度估计方法，当大多数训练标签不可用时。我们规定，即使有有限的训练标签，我们仍然可以通过检查训练过程中的预测一致性来合理地近似模型对未标记样本的置信度。我们使用训练一致性作为代理函数，并提出了一致性排名损失的信心估计。在图像分类和分割任务中，我们的方法在置信度估计方面达到了最先进的性能。此外，我们通过下游主动学习任务显示了所提出的方法的好处。代码可在https://github.com/TopoXLab/consistency-ranking-loss上获得

Overconfidence is a common issue for deep neural networks, limiting their deployment in real-world applications. To better estimate confidence, existing methods mostly focus on fully-supervised scenarios and rely on training labels. In this paper, we propose the first confidence estimation method for a semi-supervised setting, when most training labels are unavailable. We stipulate that even with limited training labels, we can still reasonably approximate the confidence of model on unlabeled samples by inspecting the prediction consistency through the training process. We use training consistency as a surrogate function and propose a consistency ranking loss for confidence estimation. On both image classification and segmentation tasks, our method achieves state-of-the-art performances in confidence estimation. Furthermore, we show the benefit of the proposed method through a downstream active learning task. The code is available at https://github.com/TopoXLab/consistency-ranking-loss

Confidence Estimation Using Unlabeled Data

文献摘要

相似文献