分发(OOD)检测和无损压缩构成了两个问题,可以通过对第一个数据集的概率模型进行训练来解决,其中在第二数据集上的后续似然评估,其中数据分布不同。通过在可能性方面定义概率模型的概括,我们表明,在图像模型的情况下,泛展能力通过本地特征主导。这激励了我们对本地自回归模型的提议,该模型专门为局部图像特征而达到改善的性能。我们将拟议的模型应用于检测任务,并在未引入其他数据的情况下实现最先进的无监督的检测性能。此外,我们使用我们的模型来构建新的无损图像压缩机:Nelloc(神经本地无损压缩机)和报告最先进的压缩率和模型大小。
translated by 谷歌翻译
基于密度的分布(OOD)检测最近显示了检测OOD图像的任务不可靠。基于各种密度比的方法实现了良好的经验性能,但是方法通常缺乏原则性的概率建模解释。在这项工作中,我们建议在建立基于能量的模型并采用不同基础分布的新框架下统一基于密度比的方法。在我们的框架下,密度比可以看作是隐式语义分布的非均衡密度。此外,我们建议通过类比率估计直接估计数据样本的密度比。与最近的工作相比,我们报告了有关OOD图像问题的竞争结果,这些工作需要对任务进行深层生成模型的培训。我们的方法使一个简单而有效的途径可以解决OOD检测问题。
translated by 谷歌翻译
最近提出的基于局部自回旋模型的神经局部无损压缩(NELLOC)已在图像压缩任务中实现了最新的(SOTA)过度分布(OOD)概括性能。除了鼓励OOD泛化外,局部模型还允许在解码阶段并行推断。在本文中,我们提出了两种平行化方案,用于本地自回归模型。我们讨论实施方案的实用性,并提供了与以前的非平行实施相比,压缩运行时获得显着增长的实验证据。
translated by 谷歌翻译
现代的深层生成模型可以为从训练分布外部提取的输入分配很高的可能性,从而对开放世界部署中的模型构成威胁。尽管已经对定义新的OOD不确定性测试时间度量的研究进行了很多关注,但这些方法并没有从根本上改变生成模型在训练中的正则和优化。特别是,生成模型被证明过于依赖背景信息来估计可能性。为了解决这个问题,我们提出了一个新颖的OOD检测频率调查学习FRL框架,该框架将高频信息纳入培训中,并指导模型专注于语义相关的功能。 FRL有效地提高了广泛的生成架构的性能,包括变异自动编码器,Glow和PixelCNN ++。在一项新的大规模评估任务中,FRL实现了最先进的表现,表现优于强大的基线可能性遗憾,同时达到了147 $ \ times $ $ $ $ $ \ times $ a的推理速度。广泛的消融表明,FRL在保留图像生成质量的同时改善了OOD检测性能。代码可在https://github.com/mu-cai/frl上找到。
translated by 谷歌翻译
可靠的异常检测对于深度学习模型的现实应用至关重要。深层生成模型产生的可能性虽然进行了广泛的研究,但仍被认为是对异常检测的不切实际的。一方面,深层生成模型的可能性很容易被低级输入统计数据偏差。其次,许多用于纠正这些偏见的解决方案在计算上是昂贵的,或者对复杂的天然数据集的推广不佳。在这里,我们使用最先进的深度自回归模型探索离群值检测:PixelCNN ++。我们表明,PixelCNN ++的偏见主要来自基于局部依赖性的预测。我们提出了两个我们称为“震动”和“搅拌”的徒转化家族,它们可以改善低水平的偏见并隔离长期依赖性对PixelCNN ++可能性的贡献。这些转换在计算上是便宜的,并且在评估时很容易应用。我们使用五个灰度和六个自然图像数据集对我们的方法进行了广泛的评估,并表明它们达到或超过了最新的离群检测性能。总而言之,轻巧的补救措施足以在具有深层生成模型的图像上实现强大的离群检测。
translated by 谷歌翻译
Discriminative neural networks offer little or no performance guarantees when deployed on data not generated by the same process as the training distribution. On such out-of-distribution (OOD) inputs, the prediction may not only be erroneous, but confidently so, limiting the safe deployment of classifiers in real-world applications. One such challenging application is bacteria identification based on genomic sequences, which holds the promise of early detection of diseases, but requires a model that can output low confidence predictions on OOD genomic sequences from new bacteria that were not present in the training data. We introduce a genomics dataset for OOD detection that allows other researchers to benchmark progress on this important problem. We investigate deep generative model based approaches for OOD detection and observe that the likelihood score is heavily affected by population level background statistics. We propose a likelihood ratio method for deep generative models which effectively corrects for these confounding background statistics. We benchmark the OOD detection performance of the proposed method against existing approaches on the genomics dataset and show that our method achieves state-of-the-art performance. We demonstrate the generality of the proposed method by showing that it significantly improves OOD detection when applied to deep generative models of images.
translated by 谷歌翻译
变形自身偏移(VAES)是具有来自深神经网络架构和贝叶斯方法的丰富代表功能的有影响力的生成模型。然而,VAE模型具有比分布(ID)输入的分配方式分配更高的可能性较高的可能性。为了解决这个问题,认为可靠的不确定性估计是对对OOC投入的深入了解至关重要。在这项研究中,我们提出了一种改进的噪声对比之前(INCP),以便能够集成到VAE的编码器中,称为INCPVAE。INCP是可扩展,可培训和与VAE兼容的,它还采用了来自INCP的优点进行不确定性估计。各种数据集的实验表明,与标准VAE相比,我们的模型在OOD数据的不确定性估计方面是优越的,并且在异常检测任务中是强大的。INCPVAE模型获得了可靠的输入不确定性估算,并解决了VAE模型中的ood问题。
translated by 谷歌翻译
深度神经网络拥有的一个重要股权是在以前看不见的数据上对分发检测(OOD)进行强大的能力。在为现实世界应用程序部署模型时,此属性对于安全目的至关重要。最近的研究表明,概率的生成模型可以在这项任务上表现不佳,这令他们寻求估计培训数据的可能性。为了减轻这个问题,我们提出了对变分性自动化器(VAE)的指数倾斜的高斯先前分配。通过此之前,我们能够使用VAE自然分配的负面日志可能性来实现最先进的结果,同时比某些竞争方法快的数量级。我们还表明,我们的模型生产高质量的图像样本,这些样本比标准高斯VAE更清晰。新的先前分配具有非常简单的实现,它使用kullback leibler发散,该kullback leibler发散,该横向leibler发散,该分解比较潜伏向量的长度与球体的半径之间的差异。
translated by 谷歌翻译
通过增强模型,输入示例,培训集和优化目标,已经提出了各种方法进行分发(OOD)检测。偏离现有工作,我们有一个简单的假设,即标准的离心模型可能已经包含有关训练集分布的足够信息,这可以利用可靠的ood检测。我们对验证这一假设的实证研究,该假设测量了模型激活的模型和分布(ID)迷你批次,发现OOD Mini-Batches的激活手段一直偏离培训数据的培训数据。此外,培训数据的激活装置可以从批量归一化层作为“自由午餐”中有效地计算或从批量归一化层次上检索。基于该观察,我们提出了一种名为神经平均差异(NMD)的新型度量,其比较了输入示例和训练数据的神经手段。利用NMD的简单性,我们提出了一种有效的OOD探测器,通过标准转发通道来计算神经手段,然后是轻量级分类器。广泛的实验表明,在检测精度和计算成本方面,NMD跨越多个数据集和模型架构的最先进的操作。
translated by 谷歌翻译
The problem of detecting the Out-of-Distribution (OoD) inputs is of paramount importance for Deep Neural Networks. It has been previously shown that even Deep Generative Models that allow estimating the density of the inputs may not be reliable and often tend to make over-confident predictions for OoDs, assigning to them a higher density than to the in-distribution data. This over-confidence in a single model can be potentially mitigated with Bayesian inference over the model parameters that take into account epistemic uncertainty. This paper investigates three approaches to Bayesian inference: stochastic gradient Markov chain Monte Carlo, Bayes by Backpropagation, and Stochastic Weight Averaging-Gaussian. The inference is implemented over the weights of the deep neural networks that parameterize the likelihood of the Variational Autoencoder. We empirically evaluate the approaches against several benchmarks that are often used for OoD detection: estimation of the marginal likelihood utilizing sampled model ensemble, typicality test, disagreement score, and Watanabe-Akaike Information Criterion. Finally, we introduce two simple scores that demonstrate the state-of-the-art performance.
translated by 谷歌翻译
Out-of-distribution detection is crucial to the safe deployment of machine learning systems. Currently, the state-of-the-art in unsupervised out-of-distribution detection is dominated by generative-based approaches that make use of estimates of the likelihood or other measurements from a generative model. Reconstruction-based methods offer an alternative approach, in which a measure of reconstruction error is used to determine if a sample is out-of-distribution. However, reconstruction-based approaches are less favoured, as they require careful tuning of the model's information bottleneck - such as the size of the latent dimension - to produce good results. In this work, we exploit the view of denoising diffusion probabilistic models (DDPM) as denoising autoencoders where the bottleneck is controlled externally, by means of the amount of noise applied. We propose to use DDPMs to reconstruct an input that has been noised to a range of noise levels, and use the resulting multi-dimensional reconstruction error to classify out-of-distribution inputs. Our approach outperforms not only reconstruction-based methods, but also state-of-the-art generative-based approaches.
translated by 谷歌翻译
最近的工作表明,变异自动编码器(VAE)与速率失真理论之间有着密切的理论联系。由此激发,我们从生成建模的角度考虑了有损图像压缩的问题。从最初是为数据(图像)分布建模设计的Resnet VAE开始,我们使用量化意识的后验和先验重新设计其潜在变量模型,从而实现易于量化和熵编码的图像压缩。除了改进的神经网络块外,我们还提出了一类强大而有效的有损图像编码器类别,超过了自然图像(有损)压缩的先前方法。我们的模型以粗略的方式压缩图像,并支持并行编码和解码,从而在GPU上快速执行。
translated by 谷歌翻译
明确的深度生成模型(DGMS),例如VAES和归一化流量,已经显示出有效的数据建模替代因素,以获得无损压缩。然而,DGMS本身通常需要大的存储空间,从而污染通过精确的数据密度估计所带来的优点。为了消除对不同目标数据集的保存单独模型的要求,我们提出了一种从预磨削的深生成模型开始的新颖设置,并将数据批量压缩,同时使用动态系统仅为一个时代调整模型。我们将此设置形式形式为DGMS的单次在线适配(OSOA),无损压缩,并在此设置下提出香草算法。实验结果表明,Vanilla OsoA可以使用一个型号为所有目标节省大量时间与训练定制模型和空间与空间。具有相同的适应步骤数或适应时间,显示Vanilla OsoA可以表现出更好的空间效率,例如47美元的空间,而不是微调预先调整预制模型并保存微调模型。此外,我们展示了OSOA的潜力,并通过显示每个批次和早期停止的多个更新的进一步空间或时间效率来激励更复杂的OSOA算法。
translated by 谷歌翻译
在值得信赖的机器学习中,这是一个重要的问题,可以识别与分配任务无关的输入的分布(OOD)输入。近年来,已经提出了许多分布式检测方法。本文的目的是识别共同的目标以及确定不同OOD检测方法的隐式评分函数。我们专注于在培训期间使用替代OOD数据的方法,以学习在测试时概括为新的未见外部分布的OOD检测分数。我们表明,内部和(不同)外部分布之间的二元歧视等同于OOD检测问题的几种不同的公式。当与标准分类器以共同的方式接受培训时,该二进制判别器达到了类似于离群暴露的OOD检测性能。此外,我们表明,异常暴露所使用的置信损失具有隐式评分函数,在训练和测试外部分配相同的情况下,以非平凡的方式与理论上最佳评分功能有所不同,这又是类似于训练基于能量的OOD检测器或添加背景类时使用的一种。在实践中,当以完全相同的方式培训时,所有这些方法的性能类似。
translated by 谷歌翻译
主体组件分析(PCA)在给定固定组件维度的一类线性模型的情况下,将重建误差最小化。概率PCA通过学习PCA潜在空间权重的概率分布,从而创建生成模型,从而添加了概率结构。自动编码器(AE)最小化固定潜在空间维度的一类非线性模型中的重建误差,在固定维度处胜过PCA。在这里,我们介绍了概率自动编码器(PAE),该自动编码器(PAE)使用归一化流量(NF)了解了AE潜在空间权重的概率分布。 PAE快速且易于训练,并在下游任务中遇到小的重建错误,样本质量高以及良好的性能。我们将PAE与差异AE(VAE)进行比较,表明PAE训练更快,达到较低的重建误差,并产生良好的样品质量,而无需特殊的调整参数或培训程序。我们进一步证明,PAE是在贝叶斯推理的背景下,用于涂抹和降解应用程序的贝叶斯推断,可以执行概率图像重建的下游任务的强大模型。最后,我们将NF的潜在空间密度确定为有希望的离群检测度量。
translated by 谷歌翻译
Accurate uncertainty quantification is a major challenge in deep learning, as neural networks can make overconfident errors and assign high confidence predictions to out-of-distribution (OOD) inputs. The most popular approaches to estimate predictive uncertainty in deep learning are methods that combine predictions from multiple neural networks, such as Bayesian neural networks (BNNs) and deep ensembles. However their practicality in real-time, industrial-scale applications are limited due to the high memory and computational cost. Furthermore, ensembles and BNNs do not necessarily fix all the issues with the underlying member networks. In this work, we study principled approaches to improve uncertainty property of a single network, based on a single, deterministic representation. By formalizing the uncertainty quantification as a minimax learning problem, we first identify distance awareness, i.e., the model's ability to quantify the distance of a testing example from the training data, as a necessary condition for a DNN to achieve high-quality (i.e., minimax optimal) uncertainty estimation. We then propose Spectral-normalized Neural Gaussian Process (SNGP), a simple method that improves the distance-awareness ability of modern DNNs with two simple changes: (1) applying spectral normalization to hidden weights to enforce bi-Lipschitz smoothness in representations and (2) replacing the last output layer with a Gaussian process layer. On a suite of vision and language understanding benchmarks, SNGP outperforms other single-model approaches in prediction, calibration and out-of-domain detection. Furthermore, SNGP provides complementary benefits to popular techniques such as deep ensembles and data augmentation, making it a simple and scalable building block for probabilistic deep learning. Code is open-sourced at https://github.com/google/uncertainty-baselines
translated by 谷歌翻译
基于生成模型的图像无损压缩算法在改善压缩比方面取得了巨大的成功。但是,即使使用最先进的AI加速芯片,它们中大多数的吞吐量也小于1 Mb/s,从而阻止了它们的大多数现实应用应用,通常需要100 MB/s。在本文中,我们提出了PILC,这是一种端到端图像无损压缩框架,使用单个NVIDIA TESLA V100 GPU实现200 Mb/s的压缩和减压,比以前最有效的速度快10倍。为了获得此结果,我们首先开发了一个AI编解码器,该AI编解码器结合了自动回归模型和VQ-VAE,在轻质设置中性能很好,然后我们设计了一个低复杂性熵编码器,可与我们的编解码器配合使用。实验表明,在多个数据集中,我们的框架压缩比PNG高30%。我们认为,这是将AI压缩推向商业用途的重要步骤。
translated by 谷歌翻译
Modeling the distribution of natural images is a landmark problem in unsupervised learning. This task requires an image model that is at once expressive, tractable and scalable. We present a deep neural network that sequentially predicts the pixels in an image along the two spatial dimensions. Our method models the discrete probability of the raw pixel values and encodes the complete set of dependencies in the image. Architectural novelties include fast twodimensional recurrent layers and an effective use of residual connections in deep recurrent networks. We achieve log-likelihood scores on natural images that are considerably better than the previous state of the art. Our main results also provide benchmarks on the diverse ImageNet dataset. Samples generated from the model appear crisp, varied and globally coherent.
translated by 谷歌翻译
机器学习模型通常会遇到与训练分布不同的样本。无法识别分布(OOD)样本,因此将该样本分配给课堂标签会显着损害模​​型的可靠性。由于其对在开放世界中的安全部署模型的重要性,该问题引起了重大关注。由于对所有可能的未知分布进行建模的棘手性,检测OOD样品是具有挑战性的。迄今为止,一些研究领域解决了检测陌生样本的问题,包括异常检测,新颖性检测,一级学习,开放式识别识别和分布外检测。尽管有相似和共同的概念,但分别分布,开放式检测和异常检测已被独立研究。因此,这些研究途径尚未交叉授粉,创造了研究障碍。尽管某些调查打算概述这些方法,但它们似乎仅关注特定领域,而无需检查不同领域之间的关系。这项调查旨在在确定其共同点的同时,对各个领域的众多著名作品进行跨域和全面的审查。研究人员可以从不同领域的研究进展概述中受益,并协同发展未来的方法。此外,据我们所知,虽然进行异常检测或单级学习进行了调查,但没有关于分布外检测的全面或最新的调查,我们的调查可广泛涵盖。最后,有了统一的跨域视角,我们讨论并阐明了未来的研究线,打算将这些领域更加紧密地融为一体。
translated by 谷歌翻译
Deep neural networks have attained remarkable performance when applied to data that comes from the same distribution as that of the training set, but can significantly degrade otherwise. Therefore, detecting whether an example is out-of-distribution (OoD) is crucial to enable a system that can reject such samples or alert users. Recent works have made significant progress on OoD benchmarks consisting of small image datasets. However, many recent methods based on neural networks rely on training or tuning with both in-distribution and out-of-distribution data. The latter is generally hard to define a-priori, and its selection can easily bias the learning. We base our work on a popular method ODIN 1 [21], proposing two strategies for freeing it from the needs of tuning with OoD data, while improving its OoD detection performance. We specifically propose to decompose confidence scoring as well as a modified input pre-processing method. We show that both of these significantly help in detection performance. Our further analysis on a larger scale image dataset shows that the two types of distribution shifts, specifically semantic shift and non-semantic shift, present a significant difference in the difficulty of the problem, providing an analysis of when ODIN-like strategies do or do not work.
translated by 谷歌翻译