Out-of-distribution (OOD) generalisation is challenging because it involves not only learning from empirical data, but also deciding among various notions of generalisation, e.g., optimising the average-case risk, worst-case risk, or interpolations thereof. While this choice should in principle be made by the model operator like medical doctors, this information might not always be available at training time. The institutional separation between machine learners and model operators leads to arbitrary commitments to specific generalisation strategies by machine learners due to these deployment uncertainties. We introduce the Imprecise Domain Generalisation framework to mitigate this, featuring an imprecise risk optimisation that allows learners to stay imprecise by optimising against a continuous spectrum of generalisation strategies during training, and a model framework that allows operators to specify their generalisation preference at deployment. Supported by both theoretical and empirical evidence, our work showcases the benefits of integrating imprecision into domain generalisation.
Epistemic Intelligence & Computation Lab, College of Computing & Data Science, Nanyang Technological University, Singapore(新加坡南洋理工大学计算与数据科学学院认知智能与计算实验室);Department of Computer Science, The University of Manchester, United Kingdom(英国曼彻斯特大学计算机科学系);Manchester Centre for AI Fundamentals, Manchester, United Kingdom(英国曼彻斯特人工智能基础研究中心);Rational Intelligence Lab, CISPA Helmholtz Center for Information Security, Germany(德国CISPA海德堡信息安全中心理性智能实验室)
Dis-AE: Multi-domain & Multi-task Generalisation on Real-World Clinical Data
University of Cambridge(剑桥大学);Addenbrooke’s Hospital, Cambridge University Hospitals(剑桥大学医院阿登布鲁克医院);Barts Health NHS Trust(巴茨健康国民保健服务信托基金);NHSBT(英国国民保健署血液与移植部门)
Are nuclear masks all you need for improved out-of-domain generalisation? A closer look at cancer classification in histopathology
University of Oslo(奥斯陆大学);Otto-von-Guericke University Magdeburg(马格德堡奥托·冯·格里克大学);Singapore Institute of Technology(新加坡科技学院);Oslo University Hospital(奥斯陆大学医院);UiT The Arctic University of Norway(挪威北极大学)
检测成功的行为对于训练智能代理至关重要。因此,可推广的奖励模型是能够学习推广其行为的代理的先决条件。在这项工作中,我们专注于开发强大的成功检测器,利用大型的预训练视觉语言模型(Flamingo,Alayrac et al.(2022))和人类奖励注释。具体地说,我们把成功检测作为一个视觉问答(VQA)问题,表示为VQA。我们研究了三个截然不同的领域的成功检测:(i)在模拟家庭中的交互式语言条件代理,(ii)真实世界的机器人操作,(iii)“在野外”的人类自我中心的视频。我们研究了基于Flamingo的成功检测模型在前两个领域中看不见的语言和视觉变化的泛化特性,并发现所提出的方法能够在分布测试场景中优于定制的奖励模型。在最后一个领域的“在野外”的人类视频,我们表明,成功检测看不见的真实视频提出了一个更具挑战性的推广任务,以确保未来的工作。我们希望我们的初步结果鼓励在现实世界中的成功检测和奖励建模的进一步工作。
Advancing Vision-based Human Action Recognition: Exploring Vision-Language CLIP Model for Generalisation in Domain-Independent Tasks
Central University of Haryana(哈里亚纳中央大学);University of New South Wales(新南威尔士大学);Østfold University College(东福尔大学学院);Norwegian University of Science and Technology(挪威科技大学)
The RL Perceptron: Generalisation Dynamics of Policy Learning in High Dimensions
Gatsby Computational Neuroscience Unit(Gatsby计算神经科学单元);UCL(大学学院);Imperial College London(伦敦帝国理工学院);International School of Advanced Studies (SISSA)(国际先进研究学校(SISSA));Trieste, Italy(意大利特里斯特);Sainsbury Wellcome Centre(萨金斯堡韦尔科中心);CIFAR Azrieli Global Scholar(CIFAR阿兹里埃利全球学者);CIFAR