Accurate estimation of aleatoric and epistemic uncertainty is crucial to build safe and reliable systems. Traditional approaches, such as dropout and ensemble methods, estimate uncertainty by sampling probability predictions from different submodels, which leads to slow uncertainty estimation at inference time. Recent works address this drawback by directly predicting parameters of prior distributions over the probability predictions with a neural network. While this approach has demonstrated accurate uncertainty estimation, it requires defining arbitrary target parameters for in-distribution data and makes the unrealistic assumption that out-of-distribution (OOD) data is known at training time.
In this work we propose the Posterior Network (PostNet), which uses Normalizing Flows to predict an individual closed-form posterior distribution over predicted probabilites for any input sample. The posterior distributions learned by PostNet accurately reflect uncertainty for in- and out-of-distribution data -- without requiring access to OOD data at training time. PostNet achieves state-of-the art results in OOD detection and in uncertainty calibration under dataset shifts.
Munich Data Science Institute（慕尼黑数据科学研究所）；Technical University of Munich（慕尼黑工业大学）
Uncertainty awareness is crucial to develop reliable machine learning models. In this work, we propose the Natural Posterior Network (NatPN) for fast and high-quality uncertainty estimation for any task where the target distribution belongs to the exponential family. Thus, NatPN finds application for both classification and general regression settings. Unlike many previous approaches, NatPN does not require out-of-distribution (OOD) data at training time. Instead, it leverages Normalizing Flows to fit a single density on a learned low-dimensional and task-dependent latent space. For any input …
University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；University of Bristol（布里斯托大学）
Typical Bayesian approaches to OOD detection use epistemic uncertainty. Surprisingly from the Bayesian perspective, there are a number of methods that successfully use aleatoric uncertainty to detect OOD points (e.g. Hendryks et al. 2018). In addition, it is difficult to use outlier exposure to improve a Bayesian OOD detection model, as it is not clear whether it is possible or desirable to increase posterior (epistemic) uncertainty at outlier points. We show that a generative model of data curation provides a principled account of aleatoric uncertainty for OOD detection. In particular, aleato…
Out-of-distribution (OOD) detection is indispensable for machine learning models deployed in the open world. Recently, the use of an auxiliary outlier dataset during training (also known as outlier exposure) has shown promising performance. As the sample space for potential OOD data can be prohibitively large, sampling informative outliers is essential. In this work, we propose a novel posterior sampling-based outlier mining framework, POEM, which facilitates efficient use of outlier data and promotes learning a compact decision boundary between ID and OOD data for improved detection. We show …
Two fundamental requirements for the deployment of machine learning models in safety-critical systems are to be able to detect out-of-distribution (OOD) data correctly and to be able to explain the prediction of the model. Although significant effort has gone into both OOD detection and explainable AI, there has been little work on explaining why a model predicts a certain data point is OOD. In this paper, we address this question by introducing the concept of an OOD counterfactual, which is a perturbed data point that iteratively moves between different OOD categories. We propose a method for…
Uncertainty-Aware Out-of-Distribution Detection with Gaussian Processes
Michigan State University（密歇根州立大学）；School of Computer Science（计算机科学学院）；University of Michigan Transportation Research Institute（密歇根大学交通研究所）；Carnegie Mellon University（卡内基梅隆大学）；University of Michigan（密歇根大学）
University of Cambridge（剑桥大学）；Alan Turing Institute（艾伦·图灵研究所）；Microsoft Research（微软研究院）
Despite their successes, deep neural networks may make unreliable predictions when faced with test data drawn from a distribution different to that of the training data, constituting a major problem for AI safety. While this has recently motivated the development of methods to detect such out-of-distribution (OoD) inputs, a robust solution is still lacking. We propose a new probabilistic, unsupervised approach to this problem based on a Bayesian variational autoencoder model, which estimates a full posterior distribution over the decoder parameters using stochastic gradient Markov chain Monte …
With the rapid development of eXplainable Artificial Intelligence (XAI), a long line of past work has shown concerns about the Out-of-Distribution (OOD) problem in perturbation-based post-hoc XAI models and explanations are socially misaligned. We explore the limitations of post-hoc explanation methods that use approximators to mimic the behavior of black-box models. Then we propose eXplanation-based Counterfactual Retraining (XCR), which extracts feature importance fastly. XCR applies the explanations generated by the XAI model as counterfactual input to retrain the black-box model to address…
Deep learning models tend not to be out-of-distribution robust primarily due to their reliance on spurious features to solve the task. Counterfactual data augmentations provide a general way of (approximately) achieving representations that are counterfactual-invariant to spurious features, a requirement for out-of-distribution (OOD) robustness. In this work, we show that counterfactual data augmentations may not achieve the desired counterfactual-invariance if the augmentation is performed by a context-guessing machine, an abstract machine that guesses the most-likely context of a given input…
University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；Google（谷歌）
Detecting out-of-distribution (OOD) inputs is critical for safely deploying deep learning models in the real world. Existing approaches for detecting OOD examples work well when evaluated on benign in-distribution and OOD samples. However, in this paper, we show that existing detection mechanisms can be extremely brittle when evaluating on in-distribution and OOD inputs with minimal adversarial perturbations which don't change their semantics. Formally, we extensively study the problem of Robust Out-of-Distribution Detection on common OOD detection approaches, and show that state-of-the-art OO…
University of Pittsburgh（匹兹堡大学）；Meta AI；University of Crete（克里特大学）
A highly accurate but overconfident model is ill-suited for deployment in critical applications such as healthcare and autonomous driving. The classification outcome should reflect a high uncertainty on ambiguous in-distribution samples that lie close to the decision boundary. The model should also refrain from making overconfident decisions on samples that lie far outside its training distribution, far-out-of-distribution (far-OOD), or on unseen samples from novel classes that lie near its training distribution (near-OOD). This paper proposes an application of counterfactual explanations in f…
Hong Kong Baptist University（香港浸会大学）；The University of Melbourne（墨尔本大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；The University of Sydney（悉尼大学）
Outlier exposure (OE) is powerful in out-of-distribution (OOD) detection, enhancing detection capability via model fine-tuning with surrogate OOD data. However, surrogate data typically deviate from test OOD data. Thus, the performance of OE, when facing unseen OOD data, can be weakened. To address this issue, we propose a novel OE-based approach that makes the model perform well for unseen OOD situations, even for unseen OOD cases. It leads to a min-max learning scheme -- searching to synthesize OOD data that leads to worst judgments and learning from such OOD data for uniform performance in …
Deep neural networks have been successful in diverse discriminative classification tasks, although, they are poorly calibrated often assigning high probability to misclassified predictions. Potential consequences could lead to trustworthiness and accountability of the models when deployed in real applications, where predictions are evaluated based on their confidence scores. Existing solutions suggest the benefits attained by combining deep neural networks and Bayesian inference to quantify uncertainty over the models' predictions for ambiguous datapoints. In this work we propose to validate a…
Learning to Augment Distributions for Out-of-Distribution Detection
Hong Kong Baptist University（香港浸会大学）；University of Technology Sydney（悉尼科技大学）；The University of Melbourne（墨尔本大学）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）
While pretrained language models achieve excellent performance on natural language understanding benchmarks, they tend to rely on spurious correlations and generalize poorly to out-of-distribution (OOD) data. Recent work has explored using counterfactually-augmented data (CAD) -- data generated by minimally perturbing examples to flip the ground-truth label -- to identify robust features that are invariant under distribution shift. However, empirical results using CAD for OOD generalization have been mixed. To explain this discrepancy, we draw insights from a linear Gaussian model and demonstr…
University of California, San Diego（加州大学圣迭戈分校）；University of California, Davis（加州大学戴维斯分校）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）
Determining whether inputs are out-of-distribution (OOD) is an essential building block for safely deploying machine learning models in the open world. However, previous methods relying on the softmax confidence score suffer from overconfident posterior distributions for OOD data. We propose a unified framework for OOD detection that uses an energy score. We show that energy scores better distinguish in- and out-of-distribution samples than the traditional approach using the softmax scores. Unlike softmax confidence scores, energy scores are theoretically aligned with the probability density o…
Centro de Informática, Universidade Federal de Pernambuco（伯南布哥联邦大学信息中心）；Montreal Institute for Learning Algorithms (MILA), Université de Montréal (UdeM)（蒙特利尔大学蒙特利尔学习算法研究所（MILA））
In this paper, we argue that the unsatisfactory out-of-distribution (OOD) detection performance of neural networks is mainly due to the SoftMax loss anisotropy and propensity to produce low entropy probability distributions in disagreement with the principle of maximum entropy. Current out-of-distribution (OOD) detection approaches usually do not directly fix the SoftMax loss drawbacks, but rather build techniques to circumvent it. Unfortunately, those methods usually produce undesired side effects (e.g., classification accuracy drop, additional hyperparameters, slower inferences, and collecti…
Modern deep learning models have achieved great success in predictive accuracy for many data modalities. However, their application to many real-world tasks is restricted by poor uncertainty estimates, such as overconfidence on out-of-distribution (OOD) data and ungraceful failing under distributional shift. Previous benchmarks have found that ensembles of neural networks (NNs) are typically the best calibrated models on OOD data. Inspired by this, we leverage recent theoretical advances that characterize the function-space prior of an ensemble of infinitely-wide NNs as a Gaussian process, ter…
Antibiotic resistance monitoring is of paramount importance in the face of this on-going global epidemic. Deep learning models trained with traditional optimization algorithms (e.g. Adam, SGD) provide poor posterior estimates when tested against out-of-distribution (OoD) antibiotic resistant/non-resistant genes. In this paper, we introduce a deep learning model trained with Stochastic Gradient Langevin Dynamics (SGLD) to classify antibiotic resistant genes. The model provides better uncertainty estimates when tested against OoD data compared to traditional optimization methods such as Adam.
Adversarial Label Invariant Graph Data Augmentations for Out-of-Distribution Generalization
Department of Computer Science, Purdue University（普渡大学计算机科学系）；Department of Computer Science and Engineering, The Ohio State University（俄亥俄州立大学计算机科学与工程系）；Department of Industrial and Systems Engineering, The Ohio State University（俄亥俄州立大学工业与系统工程系）
AUTO: Adaptive Outlier Optimization for Test-Time OOD Detection
State Key Laboratory of Multimodal Artificial Intelligence Systems, CASIA（多模态人工智能系统国家重点实验室，CASIA）；Center for Research on Intelligent Perception and Computing, CASIA（智能感知与计算研究中心，CASIA）；Center for Excellence in Brain Science and Intelligence Technology, CAS（脑科学与智能技术卓越中心，CAS）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Wrocław University of Science and Technology（弗罗茨瓦夫理工大学）
Convolutional neural networks applied for real-world classification tasks need to recognize inputs that are far or out-of-distribution (OoD) with respect to the known or training data. To achieve this, many methods estimate class-conditional posterior probabilities and use confidence scores obtained from the posterior distributions. Recent works propose to use multivariate Gaussian distributions as models of posterior distributions at different layers of the CNN (i.e., for low- and upper-level features), which leads to the confidence scores based on the Mahalanobis distance. However, this proc…
Non-negative tensor factorization models enable predictive analysis on count data. Among them, Bayesian Poisson-Gamma models can derive full posterior distributions of latent factors and are less sensitive to sparse count data. However, current inference methods for these Bayesian models adopt restricted update rules for the posterior parameters. They also fail to share the update information to better cope with the data sparsity. Moreover, these models are not endowed with a component that handles the imbalance in count data values. In this paper, we propose a novel variational auto-encoder f…
Center for Data Science, New York University（纽约大学数据科学中心）；Courant Institute of Mathematical Sciences, New York University（纽约大学库朗数学科学研究所）
Methods which utilize the outputs or feature representations of predictive models have emerged as promising approaches for out-of-distribution (OOD) detection of image inputs. However, these methods struggle to detect OOD inputs that share nuisance values (e.g. background) with in-distribution inputs. The detection of shared-nuisance out-of-distribution (SN-OOD) inputs is particularly relevant in real-world applications, as anomalies and in-distribution inputs tend to be captured in the same settings during deployment. In this work, we provide a possible explanation for SN-OOD detection failur…
Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sources
Hong Kong Baptist University（香港浸会大学）；Xidian University（西安电子科技大学）；University of Technology Sydney（悉尼科技大学）；The University of Sydney（悉尼大学）；The University of Melbourne（墨尔本大学）
Out-of-Distribution Detection in Molecular Complexes via Diffusion Models for Irregular Graphs
Seminar for Applied Mathematics, Department of Mathematics and ETH AI Center, ETH Zurich（应用数学研讨会，数学系和ETH人工智能中心，瑞士苏黎世ETH学院）；Institute for Computational Life Sciences, Zurich University of Applied Sciences（计算生命科学研究所，苏黎世应用科学大学）；Department of Chemistry, Biochemistry and Pharmaceutical Sciences, University of Bern（化学、生物化学和药学系，伯尔尼大学）
Unified Classification and Rejection: A One-versus-All Framework
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
本文提出一对其余统一框架，将 K 类开放集识别建模为仅用已知类训练的 (K+1) 类问题，并结合 OVA 与交叉熵损失，在单一分类器上兼顾闭集分类、OOD 检测和误分类检测。
Idiap Research Institute（Idiap 研究院）；Australian Institute for Machine Learning, University of Adelaide（阿德莱德大学澳大利亚机器学习研究所）；Amazon（亚马逊）
Neural networks trained with SGD were recently shown to rely preferentially on linearly-predictive features and can ignore complex, equally-predictive ones. This simplicity bias can explain their lack of robustness out of distribution (OOD). The more complex the task to learn, the more likely it is that statistical artifacts (i.e. selection biases, spurious correlations) are simpler than the mechanisms to learn. We demonstrate that the simplicity bias can be mitigated and OOD generalization improved. We train a set of similar models to fit the data in different ways using a penalty on the alig…
Learning invariant (causal) features for out-of-distribution (OOD) generalization has attracted extensive attention recently, and among the proposals invariant risk minimization (IRM) is a notable solution. In spite of its theoretical promise for linear regression, the challenges of using IRM in linear classification problems remain. By introducing the information bottleneck (IB) principle into the learning of IRM, IB-IRM approach has demonstrated its power to solve these challenges. In this paper, we further improve IB-IRM from two aspects. First, we show that the key assumption of support ov…
The detection of out of distribution samples for image classification has been widely researched. Safety critical applications, such as autonomous driving, would benefit from the ability to localise the unusual objects causing the image to be out of distribution. This paper adapts state-of-the-art methods for detecting out of distribution images for image classification to the new task of detecting out of distribution pixels, which can localise the unusual objects. It further experimentally compares the adapted methods on two new datasets derived from existing semantic segmentation datasets us…
