Few-shot OOD detection focuses on recognizing out-of-distribution (OOD) images that belong to classes unseen during training, with the use of only a small number of labeled in-distribution (ID) images. Up to now, a mainstream strategy is based on large-scale vision-language models, such as CLIP. However, these methods overlook a crucial issue: the lack of reliable OOD supervision information, which can lead to biased boundaries between in-distribution (ID) and OOD. To tackle this problem, we propose CLIP-driven Outliers Synthesis~(CLIP-OS). Firstly, CLIP-OS enhances patch-level features' perception by newly proposed patch uniform convolution, and adaptively obtains the proportion of ID-relevant information by employing CLIP-surgery-discrepancy, thus achieving separation between ID-relevant and ID-irrelevant. Next, CLIP-OS synthesizes reliable OOD data by mixing up ID-relevant features from different classes to provide OOD supervision information. Afterward, CLIP-OS leverages synthetic OOD samples by unknown-aware prompt learning to enhance the separability of ID and OOD. Extensive experiments across multiple benchmarks demonstrate that CLIP-OS achieves superior few-shot OOD detection capability.
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）
University of Pennsylvania（宾夕法尼亚大学）；SRI International（SRI国际）
Deep neural networks (DNNs) are known to produce incorrect predictions with very high confidence on out-of-distribution (OOD) inputs. This limitation is one of the key challenges in the adoption of deep learning models in high-assurance systems such as autonomous driving, air traffic management, and medical diagnosis. This challenge has received significant attention recently, and several techniques have been developed to detect inputs where the model's prediction cannot be trusted. These techniques use different statistical, geometric, or topological signatures. This paper presents a taxonomy…
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…
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 …
In an out-of-distribution (OOD) detection problem, samples of known classes(also called in-distribution classes) are used to train a special classifier. In testing, the classifier can (1) classify the test samples of known classes to their respective classes and also (2) detect samples that do not belong to any of the known classes (i.e., they belong to some unknown or OOD classes). This paper studies the problem of zero-shot out-of-distribution(OOD) detection, which still performs the same two tasks in testing but has no training except using the given known class names. This paper proposes a…
Out-of-distribution (OOD) detection has received much attention lately due to its importance in the safe deployment of neural networks. One of the key challenges is that models lack supervision signals from unknown data, and as a result, can produce overconfident predictions on OOD data. Previous approaches rely on real outlier datasets for model regularization, which can be costly and sometimes infeasible to obtain in practice. In this paper, we present VOS, a novel framework for OOD detection by adaptively synthesizing virtual outliers that can meaningfully regularize the model's decision bo…
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）
Zero-Shot Out-of-Distribution Detection with Outlier Label Exposure
Australian Institute for Machine Learning（澳大利亚机器学习研究所）；The University of Adelaide（阿德莱德大学）；School of Computing and Information Systems（计算与信息系统学院）；Singapore Management University（新加坡管理大学）
Duke University（杜克大学）；Air Force Research Laboratory（空军研究实验室）
Many real-world scenarios in which DNN-based recognition systems are deployed have inherently fine-grained attributes (e.g., bird-species recognition, medical image classification). In addition to achieving reliable accuracy, a critical subtask for these models is to detect Out-of-distribution (OOD) inputs. Given the nature of the deployment environment, one may expect such OOD inputs to also be fine-grained w.r.t. the known classes (e.g., a novel bird species), which are thus extremely difficult to identify. Unfortunately, OOD detection in fine-grained scenarios remains largely underexplored.…
COOkeD: Ensemble-based OOD detection in the era of zero-shot CLIP
Aalborg University（奥尔堡大学）；ENSTA, Institut Polytechnique de Paris（法国国立高等先进技术学校，巴黎综合理工学院）；University of Barcelona（巴塞罗那大学）；Computer Vision Center（计算机视觉中心）
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 an open-world setting. However, existing OOD detection solutions can be brittle in the open world, facing various types of adversarial OOD inputs. While methods leveraging auxiliary OOD data have emerged, our analysis on illuminative examples reveals a key insight that the majority of auxiliary OOD examples may not meaningfully improve or even hurt the decision boundary of the OOD detector, which is also observed in empirical results on real data. In this paper, we provide a theoretically motiva…
Deep neural networks have achieved great success in classification tasks during the last years. However, one major problem to the path towards artificial intelligence is the inability of neural networks to accurately detect samples from novel class distributions and therefore, most of the existent classification algorithms assume that all classes are known prior to the training stage. In this work, we propose a methodology for training a neural network that allows it to efficiently detect out-of-distribution (OOD) examples without compromising much of its classification accuracy on the test ex…
Seoul National University（首尔国立大学）；Kakao Enterprise（Kakao企业）；Hanyang University（汉阳大学）；Korea Institute for Advanced Study（韩国高等研究院）；Saige Research（赛奇研究院）
A reliable evaluation method is essential for building a robust out-of-distribution (OOD) detector. Current robustness evaluation protocols for OOD detectors rely on injecting perturbations to outlier data. However, the perturbations are unlikely to occur naturally or not relevant to the content of data, providing a limited assessment of robustness. In this paper, we propose Evaluation-via-Generation for OOD detectors (EvG), a new protocol for investigating the robustness of OOD detectors under more realistic modes of variation in outliers. EvG utilizes a generative model to synthesize plausib…
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 …
OODD: Test-time Out-of-Distribution Detection with Dynamic Dictionary
Shanghai Jiao Tong University（上海交通大学）；Tianjin University（天津大学）；The Chinese University of Hong Kong（香港中文大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
It is an important problem in trustworthy machine learning to recognize out-of-distribution (OOD) inputs which are inputs unrelated to the in-distribution task. Many out-of-distribution detection methods have been suggested in recent years. The goal of this paper is to recognize common objectives as well as to identify the implicit scoring functions of different OOD detection methods. We focus on the sub-class of methods that use surrogate OOD data during training in order to learn an OOD detection score that generalizes to new unseen out-distributions at test time. We show that binary discrim…
Long-Tailed Out-of-Distribution Detection with Refined Separate Class Learning
Nanjing Agricultural University（南京农业大学）；Nanjing University（南京大学）；Shandong University（山东大学）；Nanjing University of Posts and Telecommunications（南京邮电大学）；Southeast University（东南大学）
Wuhan University（武汉大学）；University of Wisconsin - Madison（威斯康星大学麦迪逊分校）
Out-of-distribution (OOD) detection is indispensable for safely deploying machine learning models in the wild. One of the key challenges is that models lack supervision signals from unknown data, and as a result, can produce overconfident predictions on OOD data. Recent work on outlier synthesis modeled the feature space as parametric Gaussian distribution, a strong and restrictive assumption that might not hold in reality. In this paper, we propose a novel framework, Non-Parametric Outlier Synthesis (NPOS), which generates artificial OOD training data and facilitates learning a reliable decis…
Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection
Hong Kong Baptist University（香港浸会大学）；Hefei University of Technology（合肥工业大学）；University of Nottingham（诺丁汉大学）；University of California, Santa Cruz（加州大学圣克鲁兹分校）；The University of Sydney（悉尼大学）；Sydney AI Centre（悉尼人工智能中心）
Near out-of-distribution detection (OOD) is a major challenge for deep neural networks. We demonstrate that large-scale pre-trained transformers can significantly improve the state-of-the-art (SOTA) on a range of near OOD tasks across different data modalities. For instance, on CIFAR-100 vs CIFAR-10 OOD detection, we improve the AUROC from 85% (current SOTA) to more than 96% using Vision Transformers pre-trained on ImageNet-21k. On a challenging genomics OOD detection benchmark, we improve the AUROC from 66% to 77% using transformers and unsupervised pre-training. To further improve performanc…
Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolation
CMIC, Shanghai Jiao Tong University（上海交通大学CMIC）；Shanghai AI Laboratory（上海人工智能实验室）；Sydney AI Centre, The University of Sydney（悉尼大学悉尼AI中心）；RIKEN Center for Advanced Intelligence Project（理化学研究所先进智能研究中心）；The University of Tokyo（东京大学）；Hong Kong Baptist University（香港浸会大学）
Out-of-distribution (OOD) detection is an important task in machine learning systems for ensuring their reliability and safety. Deep probabilistic generative models facilitate OOD detection by estimating the likelihood of a data sample. However, such models frequently assign a suspiciously high likelihood to a specific outlier. Several recent works have addressed this issue by training a neural network with auxiliary outliers, which are generated by perturbing the input data. In this paper, we discover that these approaches fail for certain OOD datasets. Thus, we suggest a new detection metric…
SUN YAT-SEN University（中山大学）；Qiyuan Lab（启元实验室）；JD AI Research（京东人工智能研究院）
Outlier detection tasks have been playing a critical role in AI safety. There has been a great challenge to deal with this task. Observations show that deep neural network classifiers usually tend to incorrectly classify out-of-distribution (OOD) inputs into in-distribution classes with high confidence. Existing works attempt to solve the problem by explicitly imposing uncertainty on classifiers when OOD inputs are exposed to the classifier during training. In this paper, we propose an alternative probabilistic paradigm that is both practically useful and theoretically viable for the OOD detec…
VMF-GOS: Geometry-guided virtual Outlier Synthesis for Long-Tailed OOD Detection
School of Computer and Electronic Information, Nanjing Normal University, China（南京师范大学计算机与电子信息学院）；School of Artificial Intelligence and Information Technology, Nanjing University of Chinese Medicine, China（南京中医药大学人工智能与信息技术学院）
Recent Advances in Out-of-Distribution Detection with CLIP-Like Models: A Survey
College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics（南京航空航天大学计算机科学与技术学院）；MIIT Key Laboratory of Pattern Analysis and Machine Intelligence（信息产业部模式分析与机器智能重点实验室）；Department of Computer Science, Hong Kong Baptist University（香港 Baptist 大学计算机科学系）
We ask the following question: what training information is required to design an effective outlier/out-of-distribution (OOD) detector, i.e., detecting samples that lie far away from the training distribution? Since unlabeled data is easily accessible for many applications, the most compelling approach is to develop detectors based on only unlabeled in-distribution data. However, we observe that most existing detectors based on unlabeled data perform poorly, often equivalent to a random prediction. In contrast, existing state-of-the-art OOD detectors achieve impressive performance but require …
