Current techniques for Out-of-Distribution (OoD) detection predominantly rely on quantifying predictive uncertainty and incorporating model regularization during the training phase, using either real or synthetic OoD samples. However, methods that utilize real OoD samples lack exploration and are prone to overfit the OoD samples at hand. Whereas synthetic samples are often generated based on features extracted from training data, rendering them less effective when the training and OoD data are highly overlapped in the feature space. In this work, we propose a Wasserstein-score-based generative adversarial training scheme to enhance OoD detection accuracy, which, for the first time, performs data augmentation and exploration simultaneously under the supervision of limited OoD samples. Specifically, the generator explores OoD spaces and generates synthetic OoD samples using feedback from the discriminator, while the discriminator exploits both the observed and synthesized samples for OoD detection using a predefined Wasserstein score. We provide theoretical guarantees that the optimal solutions of our generative scheme are statistically achievable through adversarial training in empirical settings. We then demonstrate that the proposed method outperforms state-of-the-art techniques on various computer vision datasets and exhibits superior generalizability to unseen OoD data.
Out-of-Distribution (OOD) detection is essential in real-world applications, which has attracted increasing attention in recent years. However, most existing OOD detection methods require many labeled In-Distribution (ID) data, causing a heavy labeling cost. In this paper, we focus on the more realistic scenario, where limited labeled data and abundant unlabeled data are available, and these unlabeled data are mixed with ID and OOD samples. We propose the Adaptive In-Out-aware Learning (AIOL) method, in which we employ the appropriate temperature to adaptively select potential ID and OOD sampl…
Shanghai Jiao Tong University（上海交通大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；Hong Kong University of Science and Technology（香港科技大学）；Tsinghua University（清华大学）
Deep learning has achieved tremendous success with independent and identically distributed (i.i.d.) data. However, the performance of neural networks often degenerates drastically when encountering out-of-distribution (OoD) data, i.e., when training and test data are sampled from different distributions. While a plethora of algorithms have been proposed for OoD generalization, our understanding of the data used to train and evaluate these algorithms remains stagnant. In this work, we first identify and measure two distinct kinds of distribution shifts that are ubiquitous in various datasets. N…
Modern neural networks can assign high confidence to inputs drawn from outside the training distribution, posing threats to models in real-world deployments. While much research attention has been placed on designing new out-of-distribution (OOD) detection methods, the precise definition of OOD is often left in vagueness and falls short of the desired notion of OOD in reality. In this paper, we present a new formalization and model the data shifts by taking into account both the invariant and environmental (spurious) features. Under such formalization, we systematically investigate how spuriou…
Deep generative models (DGMs) seem a natural fit for detecting out-of-distribution (OOD) inputs, but such models have been shown to assign higher probabilities or densities to OOD images than images from the training distribution. In this work, we explain why this behavior should be attributed to model misestimation. We first prove that no method can guarantee performance beyond random chance without assumptions on which out-distributions are relevant. We then interrogate the typical set hypothesis, the claim that relevant out-distributions can lie in high likelihood regions of the data distri…
We categorize meta-learning evaluation into two settings: $\textit{in-distribution}$ [ID], in which the train and test tasks are sampled $\textit{iid}$ from the same underlying task distribution, and $\textit{out-of-distribution}$ [OOD], in which they are not. While most meta-learning theory and some FSL applications follow the ID setting, we identify that most existing few-shot classification benchmarks instead reflect OOD evaluation, as they use disjoint sets of train (base) and test (novel) classes for task generation. This discrepancy is problematic because -- as we show on numerous benchm…
When there are unlabeled Out-Of-Distribution (OOD) data from other classes, Semi-Supervised Learning (SSL) methods suffer from severe performance degradation and even get worse than merely training on labeled data. In this paper, we empirically analyze Pseudo-Labeling (PL) in class-mismatched SSL. PL is a simple and representative SSL method that transforms SSL problems into supervised learning by creating pseudo-labels for unlabeled data according to the model's prediction. We aim to answer two main questions: (1) How do OOD data influence PL? (2) What is the proper usage of OOD data with PL?…
Neural networks have achieved impressive performance for data in the distribution which is the same as the training set but can produce an overconfident incorrect result for the data these networks have never seen. Therefore, it is essential to detect whether inputs come from out-of-distribution(OOD) in order to guarantee the safety of neural networks deployed in the real world. In this paper, we propose a simple and effective post-hoc technique, WeShort, to reduce the overconfidence of neural networks on OOD data. Our method is inspired by the observation of the internal residual structure, w…
Open-world machine learning (ML) combines closed-world models trained on in-distribution data with out-of-distribution (OOD) detectors, which aim to detect and reject OOD inputs. Previous works on open-world ML systems usually fail to test their reliability under diverse, and possibly adversarial conditions. Therefore, in this paper, we seek to understand how resilient are state-of-the-art open-world ML systems to changes in system components? With our evaluation across 6 OOD detectors, we find that the choice of in-distribution data, model architecture and OOD data have a strong impact on OOD…
Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detection
Institute for Foundations of Data Science, University of Wisconsin, Madison（数据科学基础研究院，威斯康星大学麦迪逊分校）；Department of Computer Sciences, University of Wisconsin, Madison（计算机科学系，威斯康星大学麦迪逊分校）；Department of Electrical and Computer Engineering, University of Wisconsin, Madison（电气与计算机工程系，威斯康星大学麦迪逊分校）
We often see undesirable tradeoffs in robust machine learning where out-of-distribution (OOD) accuracy is at odds with in-distribution (ID) accuracy: a robust classifier obtained via specialized techniques such as removing spurious features often has better OOD but worse ID accuracy compared to a standard classifier trained via ERM. In this paper, we find that ID-calibrated ensembles -- where we simply ensemble the standard and robust models after calibrating on only ID data -- outperforms prior state-of-the-art (based on self-training) on both ID and OOD accuracy. On eleven natural distributi…
University of Cambridge（剑桥大学）；Microsoft Research Cambridge（微软剑桥研究院）；Nokia Bell Labs Cambridge（诺基亚剑桥贝尔实验室）
Clinical machine learning models show a significant performance drop when tested in settings not seen during training. Domain generalisation models promise to alleviate this problem, however, there is still scepticism about whether they improve over traditional training. In this work, we take a principled approach to identifying Out of Distribution (OoD) environments, motivated by the problem of cross-hospital generalization in critical care. We propose model-based and heuristic approaches to identify OoD environments and systematically compare models with different levels of held-out informat…
Object recognition and viewpoint estimation lie at the heart of visual understanding. Recent works suggest that convolutional neural networks (CNNs) fail to generalize to out-of-distribution (OOD) category-viewpoint combinations, ie. combinations not seen during training. In this paper, we investigate when and how such OOD generalization may be possible by evaluating CNNs trained to classify both object category and 3D viewpoint on OOD combinations, and identifying the neural mechanisms that facilitate such OOD generalization. We show that increasing the number of in-distribution combinations …
Model-free Test Time Adaptation for Out-Of-Distribution Detection
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）；Alibaba Group（阿里巴巴集团）；Peking University（北京大学）；Meta
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）
Arizona State University（亚利桑那州立大学）；University of Illinois Chicago（伊利诺伊大学芝加哥分校）；Bytedance AI Lab（字节跳动人工智能实验室）
Machine learning algorithms typically assume that the training and test samples come from the same distributions, i.e., in-distribution. However, in open-world scenarios, streaming big data can be Out-Of-Distribution (OOD), rendering these algorithms ineffective. Prior solutions to the OOD challenge seek to identify invariant features across different training domains. The underlying assumption is that these invariant features should also work reasonably well in the unlabeled target domain. By contrast, this work is interested in the domain-specific features that include both invariant feature…
Kernel PCA for Out-of-Distribution Detection: Non-Linear Kernel Selection and Approximation
Department of Automation, Shanghai Jiao Tong University（上海交通大学自动化系）；Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University（香港理工大学电子与电气工程系）；School of Automation, Beijing Institute of Technology（北京理工大学自动化学院）；China Mobile (Shanghai) Information and Communication Technology Co., Ltd.（中国移动（上海）信息技术有限公司）；School of Computing, Macquarie University（麦考瑞大学计算机学院）
Intel labs（英特尔实验室）；Idiap Research Institute（Idiap研究所）
As deep learning methods form a critical part in commercially important applications such as autonomous driving and medical diagnostics, it is important to reliably detect out-of-distribution (OOD) inputs while employing these algorithms. In this work, we propose an OOD detection algorithm which comprises of an ensemble of classifiers. We train each classifier in a self-supervised manner by leaving out a random subset of training data as OOD data and the rest as in-distribution (ID) data. We propose a novel margin-based loss over the softmax output which seeks to maintain at least a margin $m$…
Deep neural networks are known to be overconfident when applied to out-of-distribution (OOD) inputs which clearly do not belong to any class. This is a problem in safety-critical applications since a reliable assessment of the uncertainty of a classifier is a key property, allowing the system to trigger human intervention or to transfer into a safe state. In this paper, we aim for certifiable worst case guarantees for OOD detection by enforcing not only low confidence at the OOD point but also in an $l_\infty$-ball around it. For this purpose, we use interval bound propagation (IBP) to upper b…
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；University of Chinese Academy of Sciences（中国科学院大学）
Out-of-distribution (OOD) detection is critical for preventing deep learning models from making incorrect predictions to ensure the safety of artificial intelligence systems. Especially in safety-critical applications such as medical diagnosis and autonomous driving, the cost of incorrect decisions is usually unbearable. However, neural networks often suffer from the overconfidence issue, making high confidence for OOD data which are never seen during training process and may be irrelevant to training data, namely in-distribution (ID) data. Determining the reliability of the prediction is stil…
SCOPED: Score-Curvature Out-of-distribution Proximity Evaluator for Diffusion
Department of Electrical and Computer Engineering（电气与计算机工程系）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Department of Computer Science（计算机科学系）；Cornell University（康奈尔大学）；Department of Aerospace Engineering and Engineering Mechanics（航空航天工程与工程力学系）
How Out-of-Distribution Detection Learning Theory Enhances Transformer: Learnability and Reliability
Shanghai Jiao Tong University, China（上海交通大学）；University of Oxford, UK（牛津大学）；Shanghai AI Laboratory, China（上海人工智能实验室）；University of New South Wales, Sydney, Australia（新南威尔士大学）；Shanghai Innovation Institute, China（上海创新研究院）
Dolby Laboratories（杜比实验室）；Telefónica Research（西班牙电信研究中心）；Universitat Politècnica de Catalunya（加泰罗尼亚理工大学）；Universitat Pompeu Fabra（庞培法布拉大学）
Likelihood-based generative models are a promising resource to detect out-of-distribution (OOD) inputs which could compromise the robustness or reliability of a machine learning system. However, likelihoods derived from such models have been shown to be problematic for detecting certain types of inputs that significantly differ from training data. In this paper, we pose that this problem is due to the excessive influence that input complexity has in generative models' likelihoods. We report a set of experiments supporting this hypothesis, and use an estimate of input complexity to derive an ef…
Does CLIP's Generalization Performance Mainly Stem from High Train-Test Similarity?
University of Tübingen（蒂宾根大学）；Tübingen AI Center（蒂宾根人工智能中心）；Max-Planck-Institute for Intelligent Systems, Tübingen（马克斯·普朗克智能系统研究所蒂宾根分所）；ELLIS Institute Tübingen（ELLIS研究所蒂宾根分所）
