The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps.
translated by 谷歌翻译
Providing accurate estimated time of package delivery on users' purchasing pages for e-commerce platforms is of great importance to their purchasing decisions and post-purchase experiences. Although this problem shares some common issues with the conventional estimated time of arrival (ETA), it is more challenging with the following aspects: 1) Inductive inference. Models are required to predict ETA for orders with unseen retailers and addresses; 2) High-order interaction of order semantic information. Apart from the spatio-temporal features, the estimated time also varies greatly with other factors, such as the packaging efficiency of retailers, as well as the high-order interaction of these factors. In this paper, we propose an inductive graph transformer (IGT) that leverages raw feature information and structural graph data to estimate package delivery time. Different from previous graph transformer architectures, IGT adopts a decoupled pipeline and trains transformer as a regression function that can capture the multiplex information from both raw feature and dense embeddings encoded by a graph neural network (GNN). In addition, we further simplify the GNN structure by removing its non-linear activation and the learnable linear transformation matrix. The reduced parameter search space and linear information propagation in the simplified GNN enable the IGT to be applied in large-scale industrial scenarios. Experiments on real-world logistics datasets show that our proposed model can significantly outperform the state-of-the-art methods on estimation of delivery time. The source code is available at: https://github.com/enoche/IGT-WSDM23.
translated by 谷歌翻译
开放世界对象检测(OWOD)是一个具有挑战性的计算机视觉问题,需要检测未知对象并逐渐学习已确定的未知类别。但是,它不能将未知实例区分为多个未知类。在这项工作中,我们提出了一个新颖的OWOD问题,称为未知分类的开放世界对象检测(UC-OWOD)。 UC-OWOD旨在检测未知实例并将其分类为不同的未知类别。此外,我们制定问题并设计一个两阶段的对象检测器来解决UC-OWOD。首先,使用未知的标签意见建议和未知歧视性分类头用于检测已知和未知对象。然后,构建基于相似性的未知分类和未知聚类改进模块,以区分多个未知类别。此外,设计了两个新颖的评估方案,以评估未知类别的检测。丰富的实验和可视化证明了该方法的有效性。代码可在https://github.com/johnwuzh/uc-owod上找到。
translated by 谷歌翻译
提出了一种在智能家庭中监测的老年痴呆症患者的自动人工物联网(AIOT)系统。该系统主要根据传感器数据的活性推断实现两个功能,这些功能是实时活动异常监测和疾病相关活动的趋势预测。具体而言,CASAS数据集用于训练一个随机森林(RF)模型进行活动推断。然后,通过活动推理的输出数据训练的另一个RF模型用于异常活动监测。特别是,由于其准确性,时间效率,灵活性和可解释性之间的均衡交易,因此选择了RF的RF。此外,长期记忆(LSTM)用于预测患者疾病相关的活动趋势。因此,设计用于活动推理和异常活动检测的两个RF分类器的精度分别大于99%和94%。此外,以睡眠时间为例,LSTM模型实现了准确且明显的未来趋势预测。
translated by 谷歌翻译
姿势估计对于机器人感知,路径计划等很重要。机器人姿势可以在基质谎言组上建模,并且通常通过基于滤波器的方法进行估算。在本文中,我们在存在随机噪声的情况下建立了不变扩展Kalman滤波器(IEKF)的误差公式,并将其应用于视觉辅助惯性导航。我们通过OpenVINS平台上的数值模拟和实验评估我们的算法。在Euroc公共MAV数据集上执行的仿真和实验都表明,我们的算法优于某些基于最先进的滤波器方法,例如基于Quaternion的EKF,首先估计Jacobian EKF等。
translated by 谷歌翻译
深度神经网络容易受到对抗的例子,这可以通过添加微妙的扰动来欺骗深层模型。虽然现有的攻击已经取得了有希望的结果,但它仍然在黑盒设置下留下长途来产生可转移的对抗性示例。为此,本文提出提高对抗示例的可转移性,并将双阶段特征级扰动应用于现有模型,以隐式创建一组不同的模型。然后在迭代期间由纵向集合融合这些模型。该方法被称为双级网络侵蚀(DSNE)。我们对非残留和残余网络进行全面的实验,并获得更多可转移的对抗实例,其计算成本类似于最先进的方法。特别地,对于残余网络,通过将残余块信息偏置到跳过连接,可以显着改善对抗性示例的可转移性。我们的工作为神经网络的建筑脆弱性提供了新的见解,并对神经网络的稳健性带来了新的挑战。
translated by 谷歌翻译
段4K或6K超高分辨率图像需要在图像分割中考虑额外的计算考虑。常见的策略,如淡化采样,补丁裁剪和级联模型,不能妥善解决精度和计算成本之间的余额问题。由人类在粗糙到精确水平中连续地区分物体的影响,我们提出了用于超高分辨率分割任务的连续细化模型〜(CRM)。CRM连续将特征映射与细化目标保持一致,并聚合要重建这些图像的细节。此外,我们的CRM表明其具有填补低分辨率培训图像和超高分辨率测试之间的分辨率差距的重要概括能力。我们展示了定量的绩效评估和可视化,以表明我们的提出方法在图像分割细化方面是快速有效的。代码将在https://github.com/dvlab-research/entity发布。
translated by 谷歌翻译
通过纳入缺失区域的先验知识,通常用于图像染色的辅助损失导致更好的重建性能。但是,它通常需要充分利用辅助损失的潜力需要很多努力,因为加权辅助损失不当会分散模型从染色任务中的注意力,并且辅助损失的有效性可能在培训过程中变化。此外,辅助损失的设计需要域专业知识。在这项工作中,我们介绍了辅助损耗适应(Adaption)算法动态调整辅助丢失的参数,以更好地帮助主要任务。我们的算法基于更好的辅助损耗的原理是通过梯度下降的几个步骤提高主要损失性能的原理。然后,我们检查了两个常用的辅助损失,以适应\ ac {ala}来调整它们的参数。实验结果表明,ALA诱导比固定辅助损失更具竞争力的耐受效果。特别是,只需用\ ac {ALA}结合辅助损耗,现有的染色方法可以在未经明确地结合精密网络设计或结构知识的情况下实现增加的性能。
translated by 谷歌翻译
文本分类是自然语言处理(NLP)的主要任务。最近,图神经网络(GNN)已迅速发展,并应用于文本分类任务。作为一种特殊的图形数据,该树具有更简单的数据结构,可以为文本分类提供丰富的层次结构信息。受结构熵的启发,我们通过最小化结构熵并提出提示来构造图形的编码树,该提示旨在充分利用文本中包含的文本中包含的层次信息,以完成文本分类的任务。具体来说,我们首先为每个文本建立依赖关系解析图。然后,我们设计了一种结构熵最小化算法来解码图中的关键信息,并将每个图转换为其相应的编码树。基于编码树的层次结构,通过逐层更新编码树中的非叶子节点的表示来获得整个图的表示。最后,我们介绍了层次信息在文本分类中的有效性。实验结果表明,在具有简单的结构和很少的参数的同时,提示在流行基准测试上的最新方法优于最先进的方法。
translated by 谷歌翻译
对象攻击是对象检测的现实世界中可行的。然而,大多数以前的作品都试图学习应用于对象的本地“补丁”到愚蠢的探测器,这在斜视视角变得较低。为了解决这个问题,我们提出了致密的提案攻击(DPA)来学习探测器的单件,物理和针对性的对抗性伪装。伪装是一体的,因为它们是作为一个物体的整体生成的,因为当在任意观点和不同的照明条件下拍摄时,它们保持对抗性,并且由于它们可能导致探测器被定义为特定目标类别的检测器。为了使生成的伪装在物理世界中稳健,我们介绍了改造的组合来模拟物理现象。此外,为了改善攻击,DPA同时攻击固定建议中的所有分类。此外,我们使用Unity Simulation Engine构建虚拟3D场景,以公平地和可重复地评估不同的物理攻击。广泛的实验表明,DPA优于最先进的方法,并且对于任何物体而言,它是通用的,并且对现实世界的广泛性良好,对安全关键的计算机视觉系统构成潜在的威胁。
translated by 谷歌翻译