OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detection
Duke University(杜克大学);Nanyang Technological University(南洋理工大学);Beijing University of Posts and Telecommunications(北京邮电大学);SenseTime Research(商汤科技研究院);Duke Kunshan University(昆山杜克大学);University of Wisconsin-Madison(威斯康星大学麦迪逊分校);The Australian National University(澳大利亚国立大学);EPFL(洛桑联邦理工学院)
Jingyang Zhang, Jingkang Yang, Pengyun Wang, Haoqi Wang, Yueqian Lin, Haoran Zhang, Yiyou Sun, Xuefeng Du, Yixuan Li, Ziwei Liu, Yiran Chen, Hai Li
Out-of-Distribution (OOD) detection is critical for the reliable operation of open-world intelligent systems. Despite the emergence of an increasing number of OOD detection methods, the evaluation inconsistencies present challenges for tracking the progress in this field. OpenOOD v1 initiated the unification of the OOD detection evaluation but faced limitations in scalability and scope. In response, this paper presents OpenOOD v1.5, a significant improvement from its predecessor that ensures accurate and standardized evaluation of OOD detection methodologies at large scale. Notably, OpenOOD v1.5 extends its evaluation capabilities to large-scale data sets (ImageNet) and foundation models (e.g., CLIP and DINOv2), and expands its scope to investigate full-spectrum OOD detection which considers semantic and covariate distribution shifts at the same time. This work also contributes in-depth analysis and insights derived from comprehensive experimental results, thereby enriching the knowledge pool of OOD detection methodologies. With these enhancements, OpenOOD v1.5 aims to drive advancements and offer a more robust and comprehensive evaluation benchmark for OOD detection research.
Nanyang Technological University(南洋理工大学);Beijing University of Posts and Telecommunications(北京邮电大学);Queen Mary University of London(伦敦玛丽女王大学);SenseTime Research(商汤科技研究院);Peking University(北京大学);University of Wisconsin-Madison(威斯康星大学麦迪逊分校);University of California, Berkeley(加州大学伯克利分校)
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)
Out-of-Distribution Detection Should Use Conformal Prediction (and Vice-versa?)
IRT Saint Exupery(圣埃克苏佩里IRT研究院);Artificial and Natural Intelligence Toulouse Institute(图卢兹人工与自然智能研究所);SNCF(法国国家铁路公司);Mathematical Institute of Toulouse(图卢兹数学研究所)
Enhanced countering adversarial attacks via input denoising and feature restoring
Xidian University(西安电子科技大学)
尽管事实上深度神经网络(DNN)在各种应用中已经实现了突出的性能,但是众所周知,DNN容易受到对抗性示例/样本(AE)的影响,在干净/原始样本中具有不可感知的扰动。针对现有对抗攻击防御方法破坏原始样本信息,导致目标分类器精度下降的缺点,提出了一种增强的对抗对抗攻击方法IDFR(via Input Denoising and Feature Restoring)。提出的IDFR由一个增强的输入去噪器(ID)和一个基于凸包优化的隐藏有损特征恢复器(FR)组成。在基准数据集上进行的大量实验表明,所提出的IDFR优于各种最先进的防御方法,并且对于保护目标模型免受各种对抗性黑盒或白盒攻击非常有效。\footnote{Souce code is released at: \href{https://github.com/ID-FR/IDFR}{https://github.com/ID-FR/IDFR}}
A Multi-Center Benchmark for Abdominal Disease Diagnosis and Report Generation from Non-Contrast CT
Ain Shams University(艾因夏姆斯大学);The Hong Kong University of Science and Technology(香港科技大学);University of Catania(卡塔尼亚大学);Universitat de Barcelona(巴塞罗那大学)
Domain-Enhanced Dual-Branch Model for Efficient and Interpretable Accident Anticipation
State Key Laboratory of Internet of Things for Smart City(物联网智能城市国家重点实验室);University of Macau(澳门大学);Department of Civil Engineering(土木工程系);Department of Computer and Information Science(计算机与信息科学系);College of Transportation Engineering(交通工程学院)
A Global Benchmark of Algorithms for Segmenting Late Gadolinium-Enhanced Cardiac Magnetic Resonance Imaging
Auckland Bioengineering Institute, University of Auckland(奥克兰大学生物工程研究所);Beihang University(北京航空航天大学);Peking University(北京大学);SenseTime Inc(商汤科技);Tencent Jarvis Laboratory(腾讯Jarvis实验室);Friedrich-Alexander-Universität Erlangen-Nürnberg(埃尔朗根-纽伦堡弗里德里希-亚历山大大学);The Chinese University of Hong Kong(香港中文大学);Shenzhen University(深圳大学);Wuhan University(武汉大学);Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);EPITA Research and Development Laboratory(EPITA研发实验室);Imperial College London(伦敦帝国学院);Shanghai Jiao Tong University(上海交通大学);Fudan University(复旦大学);Harbin Institute of Technology(哈尔滨工业大学);University of Bologna(博洛尼亚大学);Eindhoven University of Technology(埃因霍温理工大学);Kings College London(伦敦国王学院);University of Magdeburg(马格德堡大学);Heidelberg University Hospital(海德堡大学医院);Leiden University Medical Center(莱顿大学医学中心);Universitat Pompeu Fabra(庞培法布拉大学);Physense(Physense机构)
Enhanced Reinforcement Learning-based Process Synthesis via Quantum Computing
Department of Chemical and Biomedical Engineering, West Virginia University(西弗吉尼亚大学化学与生物医学工程系);R.F. Smith School of Chemical and Biomolecular Engineering, Cornell University(康奈尔大学R.F. Smith化学与生物分子工程学院)