Despite significant advancements in customizing text-to-image and video generation models, generating images and videos that effectively integrate multiple personalized concepts remains a challenging task. To address this, we present TweedieMix, a novel method for composing customized diffusion models during the inference phase. By analyzing the properties of reverse diffusion sampling, our approach divides the sampling process into two stages. During the initial steps, we apply a multiple object-aware sampling technique to ensure the inclusion of the desired target objects. In the later steps, we blend the appearances of the custom concepts in the de-noised image space using Tweedie's formula. Our results demonstrate that TweedieMix can generate multiple personalized concepts with higher fidelity than existing methods. Moreover, our framework can be effortlessly extended to image-to-video diffusion models, enabling the generation of videos that feature multiple personalized concepts. Results and source code are in our anonymous project page.
FuCiTNet: Improving the generalization of deep learning networks by the fusion of learned class-inherent transformations
University of Vigo(维戈大学);University of Alicante(阿利坎特大学);University of Granada(格拉纳达大学);Universitat Politècnica de Catalunya(加泰罗尼亚理工大学)
众所周知,非常小的数据集会在深度神经网络(DNN)中产生过拟合,即,网络变得高度偏向于它已经训练过的数据。这个问题通常使用迁移学习、正则化技术和/或数据增强来缓解。这项工作提出了一种新的方法,独立但与前面提到的技术互补,用于改进DNN在非常小的数据集上的泛化,其中所涉及的类共享许多视觉特征。受GANs启发,所提出的方法称为FuCiTNet(Fusion Class inherent Transformations Network,融合类固有变换网络),在问题中创建与类一样多的生成器。每个生成器$k$学习将输入图像带入k类域的变换。我们在生成器中引入分类损失来驱动特定k类变换的学习。我们的实验表明,所提出的转换提高了分类模型在三个不同的数据集的泛化。
Improving Robustness of LiDAR-Camera Fusion Model against Weather Corruption from Fusion Strategy Perspective
Nanyang Technological University(南洋理工大学);East China Normal University(华东师范大学);Agency for Science, Technology and Research (A*STAR)(新加坡科技研究局);New York University(纽约大学)
Improving weather radar by fusion and classification
JOANNEUM RESEARCH Forschungsgesellschaft mbH(约阿内研究有限责任公司);AIT Austrian Institute of Technology GmbH(奥地利技术研究所有限责任公司);Austro Control, Österreichische Gesellschaft für Zivilluftfahrt mbH(奥斯特罗管制奥地利民用航空有限责任公司);MeteoServe Wetterdienst GmbH(MeteoServe气象服务有限责任公司)
Improving Predictive Performance and Calibration by Weight Fusion in Semantic Segmentation
Valeo Schalter und Sensoren GmbH(法雷奥开关与传感器有限公司);Stellantis, Opel Automobile GmbH(斯泰兰蒂斯集团欧宝汽车有限公司);Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院);Ilmenau University of Technology(伊尔梅瑙工业大学)
基于单目图像的3D感知由于其在自动驾驶中的应用,近年来已成为一个活跃的研究领域。然而,与基于LiDAR的技术相比,包括检测和跟踪在内的单目3D感知方法通常会产生较差的性能。通过系统的分析,我们发现,每个对象的深度估计精度是一个主要的因素限制的性能。出于这种观察,我们提出了一种多级融合方法,该方法将不同的表示(RGB和伪激光雷达)和对象(轨迹)的多帧时间信息相结合,以增强每个对象的深度估计。我们提出的融合方法在Waymo Open Dataset、KITTI检测数据集和KITTI MOT数据集上实现了最先进的每对象深度估计性能。我们进一步证明,通过简单地用融合增强深度替换估计深度,我们可以在单目3D感知任务中实现显着改进,包括检测和跟踪。
EPOFusion: Exposure aware Progressive Optimization Method for Infrared and Visible Image Fusion
College of Information Engineering, Zhejiang University of Technology(浙江工业大学信息工程学院);College of Information Science and Technology, Zhejiang Shuren University(浙江树人大学信息科技学院);Department of Electrical and Electronic Engineering, The University of Hong Kong(香港大学电机电子工程系)
Improving automatic endoscopic stone recognition using a multi-view fusion approach enhanced with two-step transfer learning
Tecnologico de Monterrey, School of Engineering and Sciences, Mexico(墨西哥蒙特雷科技大学工程与科学学院);CRAN UMR 7039, Université de Lorraine and CNRS, Nancy, France(法国洛林大学CNRS CRAN UMR 7039研究中心);CINVESTAV, Guadalajara, Mexico(墨西哥瓜达拉哈拉科学技术研究所);CHRU Nancy, Service d’urologie de Brabois, Nancy, France(法国南锡布拉布瓦大学医院泌尿外科)
Improving Prognostic Performance in Resectable Pancreatic Ductal Adenocarcinoma using Radiomics and Deep Learning Features Fusion in CT Images
University of Toronto(多伦多大学);Lunenfeld-Tanenbaum Research Institute, Sinai Health System(西奈卫生系统卢嫩菲尔德-塔南鲍姆研究所);McMaster University(麦克马斯特大学);Hamilton Health Sciences(汉密尔顿健康科学中心);Sunnybrook Health Sciences Centre(桑尼布鲁克健康科学中心);Sunnybrook Research Institute(桑尼布鲁克研究所)
相机和LiDAR传感器模态提供了互补的外观和几何信息,可用于检测自动驾驶汽车应用中的3D物体。然而,当前的端到端融合方法在训练方面具有挑战性,并且性能低于最先进的仅有LiDAR的探测器。由于点云稀疏性,顺序融合方法遭受有限数量的像素和点对应,或者它们的性能被其中一种模态的检测严格限制。我们提出的解决方案,密集体素融合(DVF)是一种顺序融合方法,生成多尺度密集体素特征表示,提高低点密度区域的表现力。为了增强多模态学习,我们直接使用投影的地面实况3D限界框标签进行训练,避免了嘈杂的、特定于检测器的2D预测。DVF和多模态训练方法都可以应用于任何基于体素的LiDAR骨干。DVF在KITTI 3D汽车检测基准的已发布融合方法中排名第三,无需引入额外的可训练参数,也不需要立体图像或密集的深度标签。此外,DVF还显著提高了Waymo Open Dataset上基于体素方法的3D车辆检测性能。
Task-driven Image Fusion with Learnable Fusion Loss
Xi’an Jiaotong University(西安交通大学);ETH Zürich(苏黎世联邦理工学院);City University of Hong Kong(香港城市大学);Tsinghua University(清华大学);Northwestern Polytechnical University(西北工业大学)
MSVIT: Improving Spiking Vision Transformer Using Multi-scale Attention Fusion
China Nanhu Academy of Electronics and Information Technology(中国南湖电子信息技术研究院);University of Chinese Academy of Sciences(中国科学院大学);The Hong Kong Polytechnic University(香港理工大学);School of Systems and Computing, The University of New South Wales(新南威尔士大学系统与计算学院)
Project-and-Fuse: Improving RGB-D Semantic Segmentation via Graph Convolution Networks
Shanghai University of Engineering Science(上海工程技术大学);Leiden University(莱顿大学);Princess Nourah bint Abdulrahman University(普里丝琴·努拉·本·阿卜杜勒拉赫曼大学);Malaysia-Japan International Institute of Technology(马来西亚-日本国际理工学院)
Improving Sickle Cell Disease Classification: A Fusion of Conventional Classifiers, Segmented Images, and Convolutional Neural Networks
Institute of Exacts and Technological Sciences -- Federal University of Viçosa (UFV)(维索萨联邦大学精确与技术科学学院);School of Computer Science -- Federal University of Uberlândia (UFU)(乌贝兰迪亚联邦大学计算机科学学院)
NeuralOOD: Improving Out-of-Distribution Generalization Performance with Brain-machine Fusion Learning Framework
Faculty of Education, Capital Normal University(首都师范大学教育学院);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology, Chinese Academy of Sciences(中国科学院脑认知与类脑智能技术重点实验室);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院)
Improving Segment Anything on the Fly: Auxiliary Online Learning and Adaptive Fusion for Medical Image Segmentation
School of Computer Science and Engineering, Nanjing University of Science and Technology(南京理工大学计算机科学与工程学院);Digital Medical Research Center, School of Basic Medical Sciences, Fudan University(复旦大学基础医学院数字医学研究中心);Shanghai Jiaotong University(上海交通大学);the Chinese University of Hong Kong(香港中文大学)
PCaM: A Progressive Focus Attention-Based Information Fusion Method for Improving Vision Transformer Domain Adaptation
Westlake Institute for Advanced Studies(西湖研究学院);Centre for Artificial Intelligence(人工智能中心);State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS)(多模态人工智能系统国家重点实验室);Institute of Automation(自动化研究所);Chinese Academy of Sciences (CASIA)(中国科学院);School of Artificial Intelligence(人工智能学院);University of Chinese Academy of Sciences (UCAS)(中国科学院大学);Alibaba Group(阿里巴巴集团);School of Computer Science(计算机学院);Engineering, the Faculty of Innovation Engineering, Macau University of Science(工程学院,创新工程 faculty,澳门科学大学);Microsoft(微软公司)
A review of deep learning-based information fusion techniques for multimodal medical image classification
Inserm(法国国家健康与医学研究院);University of Western Brittany(西布列塔尼大学);IMT Atlantique(大西洋电信学院);Sorbonne University(索邦大学);Lariboisière Hospital(拉里布瓦西耶尔医院);AP-HP(巴黎公共医疗集团);Paris Cité University(巴黎城市大学);CHRU Brest(布雷斯特大学中心医院);LaTIM UMR 1101(LaTIM联合研究单位1101)