基于像素梯度不确定性的卷积神经网络用于分布外分割
Pixel-wise Gradient Uncertainty for Convolutional Neural Networks applied to Out-of-Distribution Segmentation
AI总结：
本文提出了一种基于像素梯度的不确定性估计方法，用于卷积神经网络中的分布外分割任务，实验表明其在分割性能上优于现有方法。
摘要：
近年来，深度神经网络在语义分割领域定义了最先进的水平，其预测结果被限制在预定义的语义类别集合中。它们被应用于自动驾驶等应用，尽管其类别受限的表达能力与这种开放世界场景相悖。因此，检测和分割来自其预定义语义空间之外的对象，即分布外（OoD）对象，成为最关注的问题。由于像softmax熵或贝叶斯模型这样的不确定性估计方法对错误预测敏感，这些方法是OoD检测的自然基准。在此，我们提出了一种从像素损失梯度中获取不确定性分数的方法，该方法可以在推理过程中高效计算。我们的方法对于一大类模型易于实现，不需要额外的训练或辅助数据，并且可以轻松应用于预训练的分割模型。我们的实验表明，我们的方法能够识别错误的像素分类，并在计算开销极小的情况下估计预测质量。特别是，我们在SegmentMeIfYouCan基准测试中观察到，我们的方法在OoD分割方面优于可比的基准线，明显优于其他方法。
英文摘要：
In recent years, deep neural networks have defined the state-of-the-art in semantic segmentation where their predictions are constrained to a predefined set of semantic classes. They are to be deployed in applications such as automated driving, although their categorically confined expressive power runs contrary to such open world scenarios. Thus, the detection and segmentation of objects from outside their predefined semantic space, i.e., out-of-distribution (OoD) objects, is of highest interest. Since uncertainty estimation methods like softmax entropy or Bayesian models are sensitive to erroneous predictions, these methods are a natural baseline for OoD detection. Here, we present a method for obtaining uncertainty scores from pixel-wise loss gradients which can be computed efficiently during inference. Our approach is simple to implement for a large class of models, does not require any additional training or auxiliary data and can be readily used on pre-trained segmentation models. Our experiments show the ability of our method to identify wrong pixel classifications and to estimate prediction quality at negligible computational overhead. In particular, we observe superior performance in terms of OoD segmentation to comparable baselines on the SegmentMeIfYouCan benchmark, clearly outperforming other methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
