Estimating motion in videos is an essential computer vision problem with many downstream applications, including controllable video generation and robotics. Current solutions are primarily trained using synthetic data or require tuning of situation-specific heuristics, which inherently limits these models' capabilities in real-world contexts. Despite recent developments in large-scale self-supervised learning from videos, leveraging such representations for motion estimation remains relatively underexplored. In this work, we develop Opt-CWM, a self-supervised technique for flow and occlusion estimation from a pre-trained next-frame prediction model. Opt-CWM works by learning to optimize counterfactual probes that extract motion information from a base video model, avoiding the need for fixed heuristics while training on unrestricted video inputs. We achieve state-of-the-art performance for motion estimation on real-world videos while requiring no labeled data.
IgCONDA-PET: Weakly-Supervised PET Anomaly Detection using Implicitly-Guided Attention-Conditional Counterfactual Diffusion Modeling -- a Multi-Center, Multi-Cancer, and Multi-Tracer Study
organization= Department of Physics \& Astronomy, University of British Columbia , city= Vancouver , state= BC , country= Canada;organization= Department of Integrative Oncology, BC Cancer Research Institute , city= Vancouver , state= BC , country= Canada;organization= Department of Radiology, University of British Columbia , city= Vancouver , state= BC , country= Canada
Generating healthy counterfactuals with denoising diffusion bridge models
Athinoula A. Martinos Center for Biomedical Imaging(阿提诺拉A·马丁诺生物医学成像中心);Massachusetts General Hospital and Harvard Medical School(麻省总医院和哈佛医学院);ETH Zurich(苏黎世联邦理工学院);Computer Science & Artificial Intelligence Lab(计算机科学与人工智能实验室);Hawkes Institute(哈维斯研究所);University College London(伦敦大学学院)
Diffusion Models for Counterfactual Generation and Anomaly Detection in Brain Images
University of Edinburgh(爱丁堡大学);NHS Lothian(洛锡安国民保健服务体系);UK Dementia Research Institute Centre, University of Edinburgh(英国痴呆症研究所爱丁堡中心);University of Dundee(邓迪大学)
C2RM-Seg: Causal Counterfactual Reasoning with Structural-Semantic Priors for Weakly Supervised Histopathological Tissue Segmentation
Guangxi Key Laboratory of Image and Graphic Intelligent Processing, Guilin University of Electronic Technology(广西图像图形智能处理重点实验室,桂林电子科技大学);International Joint Research Laboratory of Spatio-temporal Information and Intelligent Location Services, Guilin University of Electronic Technology(时空信息与智能定位服务国际联合研究实验室,桂林电子科技大学);School of Computer Science and Information Security, Guilin University of Electronic Technology(桂林电子科技大学计算机与信息安全学院)
Clinically-Grounded Counterfactual Reasoning for Medical Video Diagnosis
Center for Data Science in Clinical Medicine(临床医学数据科学中心);The State Key Lab of Brain-Machine Intelligence(脑机智能国家重点实验室);Department of Gynecology and Obstetrics, 7th Medical Center of Chinese PLA General Hospital(中国人民解放军第七医学中心妇产科部);School of Computer Science, Peking University(北京大学计算机学院);School of Psychological and Cognitive Sciences, Peking University(北京大学心理学与认知科学学院);State Key Lab of General AI, Peking University(通用人工智能国家重点实验室);Nat’l Eng. Research Center of Visual Technology(视觉技术国家工程研究中心);Beijing Key Laboratory of Behavior and Mental Health(北京行为与心理健康重点实验室);Embodied Intelligence Lab, PKU-Wuhan Institute for Artificial Intelligence(具身智能实验室,北京大学-武汉人工智能研究院)
Towards Desiderata-Driven Design of Visual Counterfactual Explainers
Berlin Institute for the Foundations of Learning(柏林学习与数据基础研究所);Department of Artificial Intelligence, Korea University, Seoul, Korea(人工智能系,韩国大学,首尔,韩国);Max-Planck Institute for Informatics, Saarbruecken, Germany(马克斯·普朗克信息研究所,萨尔布吕肯,德国)
Self-Supervised Representation Learning with Meta Comprehensive Regularization
Beihang University(北京航空航天大学);Institute of Software Chinese Academy of Sciences(中国科学院软件研究所);University of Chinese Academy of Sciences(中国科学院大学);Renmin University of China(中国人民大学);Meituan(美团)
Mitigating Shortcut Learning with Diffusion Counterfactuals and Diverse Ensembles
Mila - Quebec AI Institute(米拉-魁北克人工智能研究所);Université de Montréal(蒙特利尔大学);Eberhard-Karls-Universität Tübingen(埃伯哈德卡尔斯蒂宾根大学);Idiap Research Institute(伊迪亚普研究所)