Continual Learning is considered a key step toward next-generation Artificial Intelligence. Among various methods, replay-based approaches that maintain and replay a small episodic memory of previous samples are one of the most successful strategies against catastrophic forgetting. However, since forgetting is inevitable given bounded memory and unbounded tasks, how to forget is a problem continual learning must address. Therefore, beyond simply avoiding catastrophic forgetting, an under-explored issue is how to reasonably forget while ensuring the merits of human memory, including 1. storage efficiency, 2. generalizability, and 3. some interpretability. To achieve these simultaneously, our paper proposes a new saliency-augmented memory completion framework for continual learning, inspired by recent discoveries in memory completion separation in cognitive neuroscience. Specifically, we innovatively propose to store the part of the image most important to the tasks in episodic memory by saliency map extraction and memory encoding. When learning new tasks, previous data from memory are inpainted by an adaptive data generation module, which is inspired by how humans complete episodic memory. The module's parameters are shared across all tasks and it can be jointly trained with a continual learning classifier as bilevel optimization. Extensive experiments on several continual learning and image classification benchmarks demonstrate the proposed method's effectiveness and efficiency.

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.

事件摄像机最近在高动力或具有挑战性的照明情况下具有强大的常规摄像头的潜力，因此摄影机最近变得越来越受欢迎。通过同时定位和映射（SLAM）给出了可能受益于事件摄像机的重要问题。但是，为了确保在包含事件的多传感器大满贯上进展，需要新颖的基准序列。我们的贡献是使用包含基于事件的立体声摄像机，常规立体声摄像机，多个深度传感器和惯性测量单元的多传感器设置捕获的第一组基准数据集。该设置是完全硬件同步的，并且经过了准确的外部校准。所有序列都均均均均由高度准确的外部参考设备（例如运动捕获系统）捕获的地面真相数据。各个序列都包括小型和大型环境，并涵盖动态视觉传感器针对的特定挑战。

事件摄像机是受生物启发的传感器，在具有挑战性的照明条件下表现良好，并且具有高时间分辨率。但是，他们的概念与传统的基于框架的相机根本不同。事件摄像机的像素独立和不同步。他们测量对数亮度的变化，并以高度离散的时间stamp事件形式返回它们，表明自上次事件以来一定数量的相对变化。需要新的模型和算法来处理这种测量。目前的工作着眼于事件摄像机的几个运动估计问题。事件的流以时空量的一般均应翘曲为模型，并且该目标被提出为扭曲事件图像中对比度的最大化。我们的核心贡献包括针对这些通常非凸的问题得出全球最佳解决方案，从而消除了对困扰现有方法的良好初始猜测的依赖。我们的方法依赖于分支和结合的优化，并采用了针对六个不同的对比度估计函数得出的新颖和高效的递归上限和下限。通过成功应用于三个不同的事件摄像机运动估计问题，我们的方法的实际有效性证明了这一点。

最近，深度神经网络（DNN）已被广泛引入协作过滤（CF），以产生更准确的建议结果，因为它们可以捕获项目和用户之间复杂的非线性关系的能力。计算复杂性，即消耗很长的培训时间并存储大量可训练的参数。为了解决这些问题，我们提出了一种新的广泛推荐系统，称为“广泛协作过滤”（BRODCF），这是一种有效的非线性协作过滤方法。广泛的学习系统（BLS）代替DNN，用作映射功能，以学习用户和项目之间复杂的非线性关系，这些功能可以避免上述问题，同时达到非常令人满意的建议性能。但是，直接将原始评级数据馈送到BLS不可行。为此，我们提出了一个用户项目评分协作矢量预处理程序，以生成低维用户信息输入数据，该数据能够利用最相似的用户/项目的质量判断。在七个基准数据集上进行的广泛实验证实了所提出的广播算法的有效性

在更广泛的地球科学中对人工智能模型的常见需求是表示和编码各种类型的空间数据，例如点（例如，兴趣点），折线（例如，轨迹），多边形（例如，行政区域），图（例如，运输网络）或栅格（例如，遥感图像），隐藏的嵌入空间中，使得它们可以容易地结合到深度学习模型中。一个基本步骤是将单个点位置编码为嵌入空间，使得该嵌入对下游机器学习模型（例如支持向量机和神经网络）进行学习友好。我们调用此过程位置编码。但是，对位置编码的概念，其潜在应用以及需要解决的关键挑战缺乏系统审查。本文旨在填补这一差距。我们首先提供了一个正式的编码定义，并讨论了从机器学习角度从机械研究编码的必要性。接下来，我们提供关于当前地点景观研究的全面调查和讨论。我们根据其输入和编码方法将位置编码模型分类为不同类别，并基于它们是参数，多尺度，距离保存和方向意识的方式进行比较。我们证明现有的位置编码模型可以在共享配方框架下统一。我们还讨论了不同类型的空间数据的位置编码的应用。最后，我们指出了在未来需要解决的研究中的几个挑战。

联合学习（FL）根据多个本地客户端协同聚合共享全球模型，同时保持培训数据分散以保护数据隐私。但是，标准的FL方法忽略了嘈杂的客户问题，这可能会损害聚合模型的整体性能。在本文中，我们首先分析了嘈杂的客户声明，然后用不同的噪声分布模型噪声客户端（例如，Bernoulli和截断的高斯分布）。要使用嘈杂的客户，我们提出了一个简单但有效的FL框架，名为联邦嘈杂的客户学习（FED-NCL），它是一个即插即用算法，并包含两个主要组件：动态的数据质量测量（DQM）量化每个参与客户端的数据质量，以及噪声鲁棒聚合（NRA），通过共同考虑本地训练数据和每个客户端的数据质量来自适应地聚合每个客户端的本地模型。我们的FED-NCL可以轻松应用于任何标准的流行流以处理嘈杂的客户端问题。各种数据集的实验结果表明，我们的算法提高了具有嘈杂客户端的不同现实系统的性能。

时空预测是归因于时间动态的高非线性以及空间域中的复杂位置表征模式，尤其是天气预报等领域。图表卷积通常用于对气象中的空间依赖性进行建模，以处理传感器空间位置的不规则分布。在这项工作中，提出了一种用于模仿气象流动的基于图的基于图的卷积，以捕获局部空间模式。基于位置表征模式的平滑度的假设，我们提出了条件本地卷积，其共享内核在节点的局部空间上近似通过前馈网络近似，具有通过地平线所获得的坐标的本地表示作为其输入。既定的联合标准的本地坐标系保留了地理位置的方向。我们进一步提出了距离和方向缩放术语，以减少不规则空间分布的影响。卷积嵌入到经常性的神经网络架构中以模拟时间动态，导致条件本地卷积复制网络（CLCRN）。我们的模型是在真实世界的天气基准数据集上进行评估，实现了最先进的性能，具有明显的改进。我们对本地模式可视化，模型的框架选择，地平线地图等的优势进行进一步分析。

In this paper, we study the problem of knowledge-intensive text-to-SQL, in which domain knowledge is necessary to parse expert questions into SQL queries over domain-specific tables. We formalize this scenario by building a new Chinese benchmark KnowSQL consisting of domain-specific questions covering various domains. We then address this problem by presenting formulaic knowledge, rather than by annotating additional data examples. More concretely, we construct a formulaic knowledge bank as a domain knowledge base and propose a framework (ReGrouP) to leverage this formulaic knowledge during parsing. Experiments using ReGrouP demonstrate a significant 28.2% improvement overall on KnowSQL.

Weakly-supervised object localization aims to indicate the category as well as the scope of an object in an image given only the image-level labels. Most of the existing works are based on Class Activation Mapping (CAM) and endeavor to enlarge the discriminative area inside the activation map to perceive the whole object, yet ignore the co-occurrence confounder of the object and context (e.g., fish and water), which makes the model inspection hard to distinguish object boundaries. Besides, the use of CAM also brings a dilemma problem that the classification and localization always suffer from a performance gap and can not reach their highest accuracy simultaneously. In this paper, we propose a casual knowledge distillation method, dubbed KD-CI-CAM, to address these two under-explored issues in one go. More specifically, we tackle the co-occurrence context confounder problem via causal intervention (CI), which explores the causalities among image features, contexts, and categories to eliminate the biased object-context entanglement in the class activation maps. Based on the de-biased object feature, we additionally propose a multi-teacher causal distillation framework to balance the absorption of classification knowledge and localization knowledge during model training. Extensive experiments on several benchmarks demonstrate the effectiveness of KD-CI-CAM in learning clear object boundaries from confounding contexts and addressing the dilemma problem between classification and localization performance.