这项研究的目的是开发一个强大的基于深度学习的框架，以区分Covid-19，社区获得的肺炎（CAP）和基于使用各种方案和放射剂量在不同成像中心获得的胸部CT扫描的正常病例和正常情况。我们表明，虽然我们的建议模型是在使用特定扫描协议仅从一个成像中心获取的相对较小的数据集上训练的，但该模型在使用不同技术参数的多个扫描仪获得的异质测试集上表现良好。我们还表明，可以通过无监督的方法来更新模型，以应对火车和测试集之间的数据移动，并在从其他中心接收新的外部数据集时增强模型的鲁棒性。我们采用了合奏体系结构来汇总该模型的多个版本的预测。为了初始培训和开发目的，使用了171 Covid-19、60 CAP和76个正常情况的内部数据集，其中包含使用恒定的标准辐射剂量扫描方案从一个成像中心获得的体积CT扫描。为了评估模型，我们回顾了四个不同的测试集，以研究数据特征对模型性能的转移的影响。在测试用例中，有与火车组相似的CT扫描，以及嘈杂的低剂量和超低剂量CT扫描。此外，从患有心血管疾病或手术病史的患者中获得了一些测试CT扫描。这项研究中使用的整个测试数据集包含51 covid-19、28 CAP和51例正常情况。实验结果表明，我们提出的框架在所有测试集上的表现良好，达到96.15％的总准确度（95％CI：[91.25-98.74]），COVID-119，COVID-96.08％（95％CI：[86.54-99.5]，95％），[86.54-99.5]，），，），敏感性。帽敏感性为92.86％（95％CI：[76.50-99.19]）。

We propose Hierarchical ProtoPNet: an interpretable network that explains its reasoning process by considering the hierarchical relationship between classes. Different from previous methods that explain their reasoning process by dissecting the input image and finding the prototypical parts responsible for the classification, we propose to explain the reasoning process for video action classification by dissecting the input video frames on multiple levels of the class hierarchy. The explanations leverage the hierarchy to deal with uncertainty, akin to human reasoning: When we observe water and human activity, but no definitive action it can be recognized as the water sports parent class. Only after observing a person swimming can we definitively refine it to the swimming action. Experiments on ActivityNet and UCF-101 show performance improvements while providing multi-level explanations.

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.

In this paper, we present methods for two types of metacognitive tasks in an AI system: rapidly expanding a neural classification model to accommodate a new category of object, and recognizing when a novel object type is observed instead of misclassifying the observation as a known class. Our methods take numerical data drawn from an embodied simulation environment, which describes the motion and properties of objects when interacted with, and we demonstrate that this type of representation is important for the success of novel type detection. We present a suite of experiments in rapidly accommodating the introduction of new categories and concepts and in novel type detection, and an architecture to integrate the two in an interactive system.

One of the challenges for climbing gyms is to find out popular routes for the climbers to improve their services and optimally use their infrastructure. This problem must be addressed preserving both the privacy and convenience of the climbers and the costs of the gyms. To this aim, a hardware prototype is developed to collect data using accelerometer sensors attached to a piece of climbing equipment mounted on the wall, called quickdraw, that connects the climbing rope to the bolt anchors. The corresponding sensors are configured to be energy-efficient, hence becoming practical in terms of expenses and time consumption for replacement when used in large quantities in a climbing gym. This paper describes hardware specifications, studies data measured by the sensors in ultra-low power mode, detect patterns in data during climbing different routes, and develops an unsupervised approach for route clustering.

在本文中，我们提出了一种算法，以在动态场景的两对图像之间插值。尽管在过去的几年中，在框架插值方面取得了重大进展，但当前的方法无法处理具有亮度和照明变化的图像，即使很快将图像捕获也很常见。我们建议通过利用现有的光流方法来解决这个问题，这些方法对照明的变化非常健壮。具体而言，使用使用现有预训练的流动网络估算的双向流，我们预测了从中间帧到两个输入图像的流。为此，我们建议将双向流编码为由超网络提供动力的基于坐标的网络，以获得跨时间的连续表示流。一旦获得了估计的流，我们就会在现有的混合网络中使用它们来获得最终的中间帧。通过广泛的实验，我们证明我们的方法能够比最新的框架插值算法产生明显更好的结果。

在本文中，我们提出了Satformer，这是一种基于新颖的变压器解决方案，可用于布尔（SAT）解决方案。与现有的基于学习的SAT求解器不同，在问题实例级别上学习的satformer学习了难以满足的问题实例的最低限度不满意的内核（MUC），这些实例为这些问题的因果关系提供了丰富的信息。具体而言，我们应用图形神经网络（GNN）以在连接正常格式（CNF）中获得条款的嵌入。层次变压器体系结构应用于子句嵌入以捕获条款之间的关系，并且当组成UNSAT核心的条款在一起时，自我发项权的权重被学到了很高，并将其设置为低。通过这样做，Satformer有效地了解了SAT预测条款之间的相关性。实验结果表明，Satformer比现有的基于端到端学习的SAT求解器更强大。

在这项工作中，我们研究了对象检测模型的自我监督预审计的不同方法。我们首先设计一个通用框架，通过随机采样和投射框来学习从图像中学习空间一致的密集表示，并将其投影到每个增强视图，并最大程度地提高相应的盒子功能之间的相似性。我们研究文献中的现有设计选择，例如盒子生成，功能提取策略，并使用其在实例级图像表示学习技术上获得成功启发的多种视图。我们的结果表明，该方法对超参数的不同选择是可靠的，并且使用多个视图不如实例级图像表示学习所显示的那样有效。我们还设计了两个辅助任务，以通过（1）通过使用对比度损失从采样设置中预测盒子中的一个视图中的框来预测框，并且（2）使用变压器预测盒子坐标，这可能会受益。下游对象检测任务。我们发现，在标记数据上预审计的模型时，这些任务不会导致更好的对象检测性能。

测试点插入（TPI）是一种可增强可测试性的技术，特别是对于逻辑内置的自我测试（LBIST），由于其相对较低的故障覆盖率。在本文中，我们提出了一种基于DeepTPI的Deep Greatherions学习（DRL）的新型TPI方法。与以前基于学习的解决方案将TPI任务作为监督学习问题不同，我们训练了一种新颖的DRL代理，即实例化为图神经网络（GNN）和深Q学习网络（DQN）的组合，以最大程度地提高测试覆盖范围改进。具体而言，我们将电路模型为有向图并设计基于图的值网络，以估计插入不同测试点的动作值。 DRL代理的策略定义为选择具有最大值的操作。此外，我们将预先训练模型的一般节点嵌入到增强节点特征，并为值网络提出专用的可验证性注意力机制。与商业DFT工具相比，具有各种尺度的电路的实验结果表明，DEEPTPI显着改善了测试覆盖范围。这项工作的代码可在https://github.com/cure-lab/deeptpi上获得。

我们介绍了Amstertime：一个具有挑战性的数据集，可在存在严重的域移位的情况下基准视觉位置识别（VPR）。 Amstertime提供了2500张曲式曲目的图像，这些图像匹配了相同的场景，从街景与来自阿姆斯特丹市的历史档案图像数据相匹配。图像对将同一位置与不同的相机，观点和外观捕获。与现有的基准数据集不同，Amstertime直接在GIS导航平台（Mapillary）中众包。我们评估了各种基准，包括在不同相关数据集上预先培训的非学习，监督和自我监督的方法，以进行验证和检索任务。我们的结果将在地标数据集中预先培训的RESNET-101模型的最佳准确性分别验证和检索任务分别为84％和24％。此外，在分类任务中收集了阿姆斯特丹地标子集以进行特征评估。分类标签进一步用于使用Grad-CAM提取视觉解释，以检查深度度量学习模型中学习的类似视觉效果。