Discriminative out-of-distribution detection for semantic segmentation
Discriminative out-of-distribution detection for semantic segmentation
复制标题
用于语义分割的判别性分布外检测
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Sinisa Segvic
中科院分区：
文献类型：
--
作者：
Petra Bevandic;Ivan Kreso;Marin Orsic;Sinisa Segvic
大多数分类和分割数据集假设一个封闭的世界场景，其中预测被表示为在一组预定的视觉类上的分布。然而，这样的假设意味着不可避免的，往往是不明显的故障存在的分布（OOD）输入。这些故障必然会发生在大多数现实生活中的应用，因为目前的视觉本体是远远不够全面。我们建议通过对输入数据中的OOD像素进行区分性检测来解决这个问题。与最近的方法不同，我们避免通过只观察训练用于解决所需计算机视觉任务的主模型的训练数据集来做出任何决定。相反，我们训练了一个专用的OOD模型，该模型将主要训练集与更大的“背景”数据集区分开来，该数据集近似于视觉世界的多样性。我们在密集预测设置中对高分辨率自然图像进行实验。我们使用几个道路驾驶数据集作为我们的训练分布，而我们用ILSVRC数据集近似背景分布。我们在WildDash测试中评估了我们的方法，WildDash测试是目前唯一一个包含分发外图像的公共测试数据集。实验结果表明，该方法能够有效地识别出分布不均匀的像素点，并且在很大程度上优于以往的工作。
Most classification and segmentation datasets assume a closed-world scenario in which predictions are expressed as distribution over a predetermined set of visual classes. However, such assumption implies unavoidable and often unnoticeable failures in presence of out-of-distribution (OOD) input. These failures are bound to happen in most real-life applications since current visual ontologies are far from being comprehensive. We propose to address this issue by discriminative detection of OOD pixels in input data. Different from recent approaches, we avoid to bring any decisions by only observing the training dataset of the primary model trained to solve the desired computer vision task. Instead, we train a dedicated OOD model which discriminates the primary training set from a much larger "background" dataset which approximates the variety of the visual world. We perform our experiments on high resolution natural images in a dense prediction setup. We use several road driving datasets as our training distribution, while we approximate the background distribution with the ILSVRC dataset. We evaluate our approach on WildDash test, which is currently the only public test dataset that includes out-of-distribution images. The obtained results show that the proposed approach succeeds to identify out-of-distribution pixels while outperforming previous work by a wide margin.