As the data demand for deep learning models increases, active learning (AL) becomes essential to strategically select samples for labeling, which maximizes data efficiency and reduces training costs. Real-world scenarios necessitate the consideration of incomplete data knowledge within AL. Prior works address handling out-of-distribution (OOD) data, while another research direction has focused on category discovery. However, a combined analysis of real-world considerations combining AL with out-of-distribution data and category discovery remains unexplored. To address this gap, we propose Joint Out-of-distribution filtering and data Discovery Active learning (Joda) , to uniquely address both challenges simultaneously by filtering out OOD data before selecting candidates for labeling. In contrast to previous methods, we deeply entangle the training procedure with filter and selection to construct a common feature space that aligns known and novel categories while separating OOD samples. Unlike previous works, Joda is highly efficient and completely omits auxiliary models and training access to the unlabeled pool for filtering or selection. In extensive experiments on 18 configurations and 3 metrics, \ours{} consistently achieves the highest accuracy with the best class discovery to OOD filtering balance compared to state-of-the-art competitor approaches.
Friedrich-Alexander Universität Erlangen-Nürnberg (FAU)（埃尔朗根-纽伦堡弗里德里希-亚历山大大学）；Siemens Healthcare GmbH（西门子医疗有限公司）
深度神经网络在低剂量CT去噪方面取得了巨大成功。然而，这些深度神经网络中的大多数都有几十万个可训练的参数。这与神经网络固有的非线性相结合，使得深度神经网络难以理解，责任心低。在这项研究中，我们介绍了JBFnet，神经网络的低剂量CT去噪。JBFnet的体系结构实现了迭代双边滤波。联合双边滤波器（JBF）的滤波器函数是通过浅层卷积网络学习的。引导图像由深度神经网络估计。JBFnet分为四个滤波块，每个滤波块执行联合双边滤波。每个JBF块由112个可训练的参数组成，使得噪声去除过程非常简单。在滤波之后添加噪声图（NM）以保留高级特征。我们用10名患者的身体扫描数据训练JBFnet，并在AAPM低剂量CT Grand Challenge数据集上对其进行测试。我们将JBFnet与最先进的深度学习网络进行比较。JBFnet在去除噪声的同时保留结构方面优于测试数据集上的CPCE 3D，GAN和深度GFnet。我们进行了几次消融研究，以测试我们的网络架构和训练方法的性能。我们目前的设置实现了最佳性能，同时仍然保持行为问责制。
联合图像滤波器用于在诸如提高空间分辨率和抑制噪声的任务中从用作目标图像之前的引导图像传递结构细节。基于卷积神经网络（CNN）的先前方法结合空间不变核的非线性激活来估计结构细节并回归滤波结果。在本文中，我们学习显式稀疏和空间变化的内核。我们提出了一个CNN架构及其有效的实现，称为变形核网络（DKN），输出的邻居和相应的权重集自适应每个像素。然后将滤波结果计算为加权平均。我们还提出了一个快速版本的DKN，运行速度约为17倍的大小为640 x 480的图像。我们证明了我们的模型在深度图上采样，显着图上采样，跨模态图像复原，纹理去除和语义分割的任务的有效性和灵活性。特别是，我们表明，稀疏采样的3 × 3内核的加权平均过程在所有情况下都优于最先进的显着保证金。
Joint Discovery of Object States and Manipulation Actions
Département d’informatique de l’ENS, École normale supérieure, CNRS, PSL Research University（巴黎高等师范学院计算机科学系、法国国家科学研究中心、巴黎文理研究大学）；INRIA（法国国家信息与自动化研究所）；Czech Institute of Informatics, Robotics and Cybernetics at the Czech Technical University in Prague（布拉格捷克理工大学信息学、机器人与控制论研究所）；Department of CS & OR (DIRO), Université de Montréal（蒙特利尔大学计算机科学与运筹学系）
JPGNet: Joint Predictive Filtering and Generative Network for Image Inpainting
College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）；University of South Carolina（南卡罗来纳大学）；Alibaba Group（阿里巴巴集团）；Cleveland State University（克利夫兰州立大学）；Nanyang Technological University（南洋理工大学）；Zhejiang Sci-Tech University（浙江理工大学）
A Clonal Selection Algorithm with Levenshtein Distance based Image Similarity in Multidimensional Subjective Tourist Information and Discovery of Cryptic Spots by Interactive GHSOM
Progressive Per-Branch Depth Optimization for DEFOM-Stereo and SAM3 Joint Analysis in UAV Forestry Applications
Centre for Data Science and Artificial Intelligence（数据科学与人工智能中心）；Victoria University of Wellington（威灵顿维多利亚大学）；Department of Computer Science and Software Engineering（计算机科学与软件工程系）；University of Canterbury（坎特伯雷大学）
Novel Class Discovery for Point Cloud Segmentation via Joint Learning of Causal Representation and Reasoning
School of Artificial Intelligence, College of Intelligence and Computing, Tianjin University, China（人工智能学院、智能与计算学院、天津大学）；School of Computer Science and Information Engineering, Hefei University of Technology, China（计算机科学与信息工程学院、合肥工业大学）
