This paper proposes a method for OOD detection. Questioning the premise of previous studies that ID and OOD samples are separated distinctly, we consider samples lying in the intermediate of the two and use them for training a network. We generate such samples using multiple image transformations that corrupt inputs in various ways and with different severity levels. We estimate where the generated samples by a single image transformation lie between ID and OOD using a network trained on clean ID samples. To be specific, we make the network classify the generated samples and calculate their mean classification accuracy, using which we create a soft target label for them. We train the same network from scratch using the original ID samples and the generated samples with the soft labels created for them. We detect OOD samples by thresholding the entropy of the predicted softmax probability. The experimental results show that our method outperforms the previous state-of-the-art in the standard benchmark tests. We also analyze the effect of the number and particular combinations of image corrupting transformations on the performance.
翻译:本文建议了一种检测 OOD 的方法。 质疑先前研究的前提, 即ID 和 OOD 样本是分开的, 我们考虑在两者中间的样本, 并用它们来训练网络。 我们使用多种图像转换方法生成这些样本, 以各种方式和不同严重程度腐蚀投入。 我们用一个经过清洁的ID 样本培训的网络来估计在ID 和 OOD 之间生成的样本。 具体地说, 我们让网络对生成的样本进行分类, 并计算其平均分类准确性, 我们用这些样本创建一个软目标标签。 我们用原始的 ID 样本和为它们创建的软标签来从零开始对生成的样本进行培训。 我们通过设定预测软通缩概率的酶来检测 OOD 样本。 实验结果显示, 我们的方法超过了标准基准测试中以前的状态。 我们还分析了图像腐蚀变的数值和特定组合对性能的影响 。