In this work, we propose Cell Variational Information Bottleneck Network (cellVIB), a convolutional neural network using information bottleneck mechanism, which can be combined with the latest feedforward network architecture in an end-to-end training method. Our Cell Variational Information Bottleneck Network is constructed by stacking VIB cells, which generate feature maps with uncertainty. As layers going deeper, the regularization effect will gradually increase, instead of directly adding excessive regular constraints to the output layer of the model as in Deep VIB. Under each VIB cell, the feedforward process learns an independent mean term and an standard deviation term, and predicts the Gaussian distribution based on them. The feedback process is based on reparameterization trick for effective training. This work performs an extensive analysis on MNIST dataset to verify the effectiveness of each VIB cells, and provides an insightful analysis on how the VIB cells affect mutual information. Experiments conducted on CIFAR-10 also prove that our cellVIB is robust against noisy labels during training and against corrupted images during testing. Then, we validate our method on PACS dataset, whose results show that the VIB cells can significantly improve the generalization performance of the basic model. Finally, in a more complex representation learning task, face recognition, our network structure has also achieved very competitive results.
Learning to Learn with Variational Information Bottleneck for Domain Generalization
University of Amsterdam(阿姆斯特丹大学);Nankai University(南开大学);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学);Duke University(杜克大学);Inception Institute of Artificial Intelligence(起源人工智能研究院)
VIB-Probe: Detecting and Mitigating Hallucinations in Vision-Language Models via Variational Information Bottleneck
College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China(复旦大学计算机科学与人工智能学院,上海,中国);Shanghai Key Laboratory of Intelligent Information Processing(上海智能信息处理重点实验室)
East China Normal University(华东师范大学);Huawei Technologies(华为技术有限公司);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Xiamen University(厦门大学);Shanghai Jiao Tong University(上海交通大学);Shenzhen University(深圳大学);University of Sydney(悉尼大学)
Semi-supervised variational autoencoder for cell feature extraction in multiplexed immunofluorescence images
School of Computer Science and Engineering, University of New South Wales(新南威尔士大学计算机科学与工程学院);Garvan Institute of Medical Research(加文医学研究所);St George Hospital(圣乔治医院);School of Clinical Medicine, Faculty of Medicine, UNSW Sydney(新南威尔士大学悉尼分校医学院临床学院);NSW Health Pathology, St. George Hospital(新南威尔士州卫生病理服务局圣乔治医院分部);University of Technology Sydney(悉尼科技大学)
VNDUQE: Information-Theoretic Novelty Detection using Deep Variational Information Bottleneck
1 Nondestructive Evaluation Lab, Department of Electrical;Computer Engineering Michigan State University East Lansing, MI Email;2 Department of Electrical
Multimodal Analysis of White Blood Cell Differentiation in Acute Myeloid Leukemia Patients using a β-Variational Autoencoder
Institute of AI for Health, Helmholtz Zentrum München – German Research Center for Environmental Health(慕尼黑亥姆霍兹中心人工智能健康研究所(德国环境健康研究中心));University of Trento(特伦托大学);Technical University of Munich(慕尼黑工业大学);Ludwig-Maximilians University Munich(慕尼黑大学);Johns Hopkins University(约翰斯·霍普金斯大学)
How Convolutional Neural Network Architecture Biases Learned Opponency and Colour Tuning
University of Southampton(南安普顿大学);Vision Learning and Control, Electronics and Computer Science, University of Southampton(南安普顿大学视觉学习与控制、电子与计算机科学(注:机构粒度要求到大学级别,此处完整机构为University of Southampton,其余为其内部部门,按要求提取到大学级别))