论文标题
由Real NVP产生的合成异常值的密集开放式识别
Dense open-set recognition with synthetic outliers generated by Real NVP
论文作者
论文摘要
当今的深层模型通常无法检测不属于培训分布的输入。这引起了自信的错误预测，这可能会导致许多重要的应用领域（例如医疗保健和自动驾驶）造成毁灭性后果。有趣的是，歧视和生成模型似乎都受到同样的影响。因此，这种脆弱性代表了一个重要的研究挑战。我们考虑一种基于歧视性训练和共同学习的合成异常值的异常检测方法。我们通过对RNVP模型进行采样来获得合成异常值，该模型经过联合训练以生成训练分布边界的数据点。我们表明，这种方法可以适应同时的语义分割和密集的异常值检测。我们介绍了CIFAR-10上的图像分类实验，以及三个现有数据集（Strethazars，WD-Pascal，fishysyscapes Lost＆cound）的语义分割实验，还有一个贡献数据集。尽管只有一个前向传球产生预测，但我们的模型在最先进的情况下表现竞争力。
Today's deep models are often unable to detect inputs which do not belong to the training distribution. This gives rise to confident incorrect predictions which could lead to devastating consequences in many important application fields such as healthcare and autonomous driving. Interestingly, both discriminative and generative models appear to be equally affected. Consequently, this vulnerability represents an important research challenge. We consider an outlier detection approach based on discriminative training with jointly learned synthetic outliers. We obtain the synthetic outliers by sampling an RNVP model which is jointly trained to generate datapoints at the border of the training distribution. We show that this approach can be adapted for simultaneous semantic segmentation and dense outlier detection. We present image classification experiments on CIFAR-10, as well as semantic segmentation experiments on three existing datasets (StreetHazards, WD-Pascal, Fishyscapes Lost & Found), and one contributed dataset. Our models perform competitively with respect to the state of the art despite producing predictions with only one forward pass.
