The ability of the deep learning model to recognize when a sample falls outside its learned distribution is critical for safe and reliable deployment. Recent state-of-the-art out-of-distribution (OOD) detection methods leverage activation shaping to improve the separation between in-distribution (ID) and OOD inputs. These approaches resort to sample-specific scaling but apply a static percentile threshold across all samples regardless of their nature, resulting in suboptimal ID-OOD separability. In this work, we propose \textbf{AdaSCALE}, an adaptive scaling procedure that dynamically adjusts the percentile threshold based on a sample's estimated OOD likelihood. This estimation leverages our key observation: OOD samples exhibit significantly more pronounced activation shifts at high-magnitude activations under minor perturbation compared to ID samples. AdaSCALE enables stronger scaling for likely ID samples and weaker scaling for likely OOD samples, yielding highly separable energy scores. Our approach achieves state-of-the-art OOD detection performance, outperforming the latest rival OptFS by 14.94% in near-OOD and 21.67% in far-OOD datasets in average FPR@95 metric on the ImageNet-1k benchmark across eight diverse architectures. The code is available at: https://github.com/sudarshanregmi/AdaSCALE/
ANTS: Adaptive Negative Textual Space Shaping for OOD Detection via Test-Time MLLM Understanding and Reasoning
The Hong Kong Polytechnic University（香港理工大学）；Eastern Institute of Technology, Ningbo（宁波东部技术研究院）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；Zhongguancun Academy（中关村学院）
In vision-enabled autonomous systems such as robots and autonomous cars, video object detection plays a crucial role, and both its speed and accuracy are important factors to provide reliable operation. The key insight we show in this paper is that speed and accuracy are not necessarily a trade-off when it comes to image scaling. Our results show that re-scaling the image to a lower resolution will sometimes produce better accuracy. Based on this observation, we propose a novel approach, dubbed AdaScale, which adaptively selects the input image scale that improves both accuracy and speed for v…
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）
Your Data Is Not Perfect: Towards Cross-Domain Out-of-Distribution Detection in Class-Imbalanced Data
College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算学院和数据科学学院）；KINDI Computing Research Center, College of Engineering, Qatar University, Doha（卡塔尔大学工程学院KINDI计算研究中心，多哈）
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Science and Technology Beijing（北京科技大学）；University of Chinese Academy of Sciences（中国科学院大学）；HK Institute of Science and Innovation（香港科学创新研究院）
There is an increasing need to determine whether inputs are out-of-distribution (\emph{OOD}) for safely deploying machine learning models in the open world scenario. Typical neural classifiers are based on the closed world assumption, where the training data and the test data are drawn \emph{i.i.d.} from the same distribution, and as a result, give over-confident predictions even faced with \emph{OOD} inputs. For tackling this problem, previous studies either use real outliers for training or generate synthetic \emph{OOD} data under strong assumptions, which are either costly or intractable to…
Adaptive Residual Transformation for Enhanced Feature-Based OOD Detection in SAR Imagery
Next Generation Defence Multidisciplinary Technology Research Center, Pohang University of Science and Technology（浦项科技大学下一代国防多学科技术研究中心）；Pohang University of Science and Technology（浦项科技大学）
Adaptive Hierarchical Graph Cut for Multi-granularity Out-of-distribution Detection
Interdisciplinary Graduate Programme, Nanyang Technological University（新加坡国立大学跨学科研究生项目）；College of Computing and Data Science, Nanyang Technological University（新加坡国立大学计算与数据科学学院）；KINDI Computing Research Center, College of Engineering, Qatar University（卡塔尔大学工程学院KINDI计算研究中心）
How to Achieve Prototypical Birth and Death for OOD Detection?
School of Computer and Electronic Information, Nanjing Normal University（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（南京中医药大学人工智能与信息技术学院）；School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University, Shenzhen（中山大学深圳校区网络安全科学与技术学院）；Tohoku University（东北大学）
GOOD: Training-Free Guided Diffusion Sampling for Out-of-Distribution Detection
Nanjing University（南京大学）；Fudan University（复旦大学）；Carnegie Mellon University（卡内基梅隆大学）；Chinese Academy of Sciences（中国科学院）；Nanyang Technological University（南洋理工大学）
University of Oxford（牛津大学）；Meta AI；Five AI Ltd.（Five人工智能有限公司）
It is now well known that neural networks can be wrong with high confidence in their predictions, leading to poor calibration. The most common post-hoc approach to compensate for this is to perform temperature scaling, which adjusts the confidences of the predictions on any input by scaling the logits by a fixed value. Whilst this approach typically improves the average calibration across the whole test dataset, this improvement typically reduces the individual confidences of the predictions irrespective of whether the classification of a given input is correct or incorrect. With this insight,…
The Hong Kong Polytechnic University（香港理工大学）；The Australian National University（澳大利亚国立大学）
Model calibration usually requires optimizing some parameters (e.g., temperature) w.r.t an objective function (e.g., negative log-likelihood). In this paper, we report a plain, important but often neglected fact that the objective function is influenced by calibration set difficulty, i.e., the ratio of the number of incorrectly classified samples to that of correctly classified samples. If a test set has a drastically different difficulty level from the calibration set, the optimal calibration parameters of the two datasets would be different. In other words, a calibrator optimal on the calibr…
Quantization Meets OOD: Generalizable Quantization-aware Training from a Flatness Perspective
SIGS, Tsinghua University（清华大学信息科学技术系）；Key Laboratory of Pervasive Computing, Ministry of Education（教育部 pervasive 计算重点实验室）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）；MMLab, The Chinese University of Hong Kong（香港中文大学 MMLab）
Unpaired image-to-image translation refers to learning inter-image-domain mapping in an unsupervised manner. Existing methods often learn deterministic mappings without explicitly modelling the robustness to outliers or predictive uncertainty, leading to performance degradation when encountering unseen out-of-distribution (OOD) patterns at test time. To address this limitation, we propose a novel probabilistic method called Uncertainty-aware Generalized Adaptive Cycle Consistency (UGAC), which models the per-pixel residual by generalized Gaussian distribution, capable of modelling heavy-tailed…
Image-to-image translation is an ill-posed problem as unique one-to-one mapping may not exist between the source and target images. Learning-based methods proposed in this context often evaluate the performance on test data that is similar to the training data, which may be impractical. This demands robust methods that can quantify uncertainty in the prediction for making informed decisions, especially for critical areas such as medical imaging. Recent works that employ conditional generative adversarial networks (GANs) have shown improved performance in learning photo-realistic image-to-image…
Xi’an Jiaotong University（西安交通大学）；Institute of Artificial Intelligence and Robotics（人工智能与机器人研究所）
Encouraging progress has been made towards Visual Question Answering (VQA) in recent years, but it is still challenging to enable VQA models to adaptively generalize to out-of-distribution (OOD) samples. Intuitively, recompositions of existing visual concepts (\ie, attributes and objects) can generate unseen compositions in the training set, which will promote VQA models to generalize to OOD samples. In this paper, we formulate OOD generalization in VQA as a compositional generalization problem and propose a graph generative modeling-based training scheme (X-GGM) to implicitly model the proble…
On the Robustness of Open-World Test-Time Training: Self-Training with Dynamic Prototype Expansion
South China University of Technology（华南理工大学）；Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局（A*STAR）信息通信研究院（I2R））
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…
