Parametric and non-parametric classifiers often have to deal with real-world data, where corruptions like noise, occlusions, and blur are unavoidable - posing significant challenges. We present a probabilistic approach to classify strongly corrupted data and quantify uncertainty, despite the model only having been trained with uncorrupted data. A semi-supervised autoencoder trained on uncorrupted data is the underlying architecture. We use the decoding part as a generative model for realistic data and extend it by convolutions, masking, and additive Gaussian noise to describe imperfections. This constitutes a statistical inference task in terms of the optimal latent space activations of the underlying uncorrupted datum. We solve this problem approximately with Metric Gaussian Variational Inference (MGVI). The supervision of the autoencoder's latent space allows us to classify corrupted data directly under uncertainty with the statistically inferred latent space activations. Furthermore, we demonstrate that the model uncertainty strongly depends on whether the classification is correct or wrong, setting a basis for a statistical "lie detector" of the classification. Independent of that, we show that the generative model can optimally restore the uncorrupted datum by decoding the inferred latent space activations.
翻译:摘要:参数化和非参数化分类器经常需要处理现实世界的数据,在这些数据中,噪声、遮挡和模糊等损伤是不可避免的,因此会带来重大挑战。我们提出了一种概率方法来分类强烈损坏的数据并量化其不确定性,尽管该模型只经过未受损数据的训练。半监督自编码器是底层体系结构。我们使用解码部分作为生成模型来模拟现实数据,通过卷积、掩模和加性高斯噪声来描述缺陷。这构成了一个统计推断任务,涉及到底层未受损数据的最佳潜在空间激活。我们使用度量高斯变分推断(Metric Gaussian Variational Inference,MGVI)来近似解决这个问题。自编码器潜在空间的监督允许我们直接分类带损坏的数据,并使用统计推断的潜在空间激活来量化不确定性。此外,我们证明了模型的不确定性强烈依赖于分类是否正确,为分类的统计"撒谎检测器"奠定了基础。独立于此,我们展示了,通过解码推断的潜在空间激活,生成模型可以最优地恢复未受损的数据。