Deep Neural Networks (DNNs) have been ubiquitously adopted in internet of things and are becoming an integral of our daily life. When tackling the evolving learning tasks in real world, such as classifying different types of objects, DNNs face the challenge to continually retrain themselves according to the tasks on different edge devices. Federated continual learning is a promising technique that offers partial solutions but yet to overcome the following difficulties: the significant accuracy loss due to the limited on-device processing, the negative knowledge transfer caused by the limited communication of non-IID data, and the limited scalability on the tasks and edge devices. In this paper, we propose FedKNOW, an accurate and scalable federated continual learning framework, via a novel concept of signature task knowledge. FedKNOW is a client side solution that continuously extracts and integrates the knowledge of signature tasks which are highly influenced by the current task. Each client of FedKNOW is composed of a knowledge extractor, a gradient restorer and, most importantly, a gradient integrator. Upon training for a new task, the gradient integrator ensures the prevention of catastrophic forgetting and mitigation of negative knowledge transfer by effectively combining signature tasks identified from the past local tasks and other clients' current tasks through the global model. We implement FedKNOW in PyTorch and extensively evaluate it against state-of-the-art techniques using popular federated continual learning benchmarks. Extensive evaluation results on heterogeneous edge devices show that FedKNOW improves model accuracy by 63.24% without increasing model training time, reduces communication cost by 34.28%, and achieves more improvements under difficult scenarios such as large numbers of tasks or clients, and training different complex networks.

关于无监督的域适应性（UDA）的广泛研究已将有限的实验数据集深入学习到现实世界中无约束的领域。大多数UDA接近通用嵌入空间中的对齐功能，并将共享分类器应用于目标预测。但是，由于当域差异很大时可能不存在完全排列的特征空间，因此这些方法受到了两个局限性。首先，由于缺乏目标标签监督，强制域的比对会恶化目标域的可区分性。其次，源监督分类器不可避免地偏向源数据，因此它在目标域中的表现可能不佳。为了减轻这些问题，我们建议在两个集中在不同领域的空间中同时进行特征对齐，并为每个空间创建一个针对该域的面向域的分类器。具体而言，我们设计了一个面向域的变压器（DOT），该变压器（DOT）具有两个单独的分类令牌，以学习不同的面向域的表示形式和两个分类器，以保持域的可区分性。理论保证的基于对比度的对齐和源指导的伪标签细化策略被用来探索域名和特定信息。全面的实验验证了我们的方法在几个基准上实现了最先进的方法。

DETR风格的检测器在内域场景中脱颖而出，但是它们在域移位设置中的属性却没有探索。本文旨在根据两个发现，在域移位设置上使用DETR式检测器建立一个简单但有效的基线。首先，减轻主链的域移动，解码器输出功能在获得有利的结果方面表现出色。对于另一种高级域对准方法，这两个部分都进一步增强了性能。因此，我们提出了对象感知的对准（OAA）模块和最佳基于运输的比对（OTA）模块，以在骨干和检测器的输出上实现全面的域对齐。 OAA模块将伪标签标识的前景区域对齐骨干输出中的伪标签，从而导致基于域的不变特征。 OTA模块利用切成薄片的Wasserstein距离来最大化位置信息的保留，同时最大程度地减少解码器输出中的域间隙。我们将调查结果和对齐模块实施到我们的适应方法中，并基准在域移位设置上基于DETR风格的检测器。在各种领域自适应场景上进行的实验验证了我们方法的有效性。

深度神经网络（DNN）已成为移动和嵌入式系统中的普遍存在的技术，用于图像/对象识别和分类。执行多个DNN的趋势同时加剧了资源受限移动设备上满足严格延迟/准确性要求的现有限制。现有技术通过根据资源动态缩放模型大小来探索精度资源权衡的光。然而，这种模型缩放方法接近迫在眉睫的挑战：（i）模型尺寸的大空间探索，（ii）对不同模型组合的培训时间非常长。在本文中，我们介绍了Legodnn，一种用于在移动视觉系统中运行多DNN工作负载的轻质块粒度缩放解决方案。 Legodnn仅通过在DNN中提取和培训少数常见块（例如，在VGG和RENET中的VGG和8中的8中）来保证短模型培训时间。在运行时，Legodnn最佳地结合了这些块的后代模型，以最大限度地在特定资源和延迟约束下最大限度地提高精度，同时通过DNN的智能块级缩放来降低切换开销。我们在Tensorflow Lite中实现Legodnn，并通过一组普遍的DNN模型，广泛地评估了最先进的技术（浮标缩放，知识蒸馏和模型压缩）。评估结果表明，乐高达在模型尺寸下提供了1,296倍至279,936倍，而在不增加训练时间的情况下，推断准确性的提高高达31.74％，降低缩放能耗减少了71.07％。

域适应（da）尝试将知识从标记的源域传输到从源的不同分发的未标记的目标域。为此，DA方法包括源分类目标，以提取源知识和域对齐目标以减少域移位，确保知识转移。通常，前DA方法采用一些重量的超参数来线性地结合培训目标来形成整体目标。然而，由于域移位，这些目标的梯度方向可能彼此冲突。在这种情况下，线性优化方案可能会降低整体目标值，以损坏其中一个培训目标，导致限制解决方案。在本文中，我们从基于梯度的角度来看了DA的优化方案。我们提出了帕累托域适应（Paretoda）方法来控制整体优化方向，旨在协同优化所有培训目标。具体地，为了达到目标域的理想解决方案，我们设计了模拟目标分类的替代损失。为了提高目标预测准确性以支持模拟，我们提出了一种目标预测精炼机制，其通过贝叶斯定理利用域标签。另一方面，由于对象的加权方案的先验知识通常无法指导优化来接近目标域上的最佳解决方案，因此我们提出了一种动态的偏好机制，以动态指导我们的合作优化通过替代损失的梯度保持未标记的目标数据集。关于图像分类和语义分割基准的广泛实验证明了Paretoda的有效性

最近，无监督的域适应是一种有效的范例，用于概括深度神经网络到新的目标域。但是，仍有巨大的潜力才能达到完全监督的性能。在本文中，我们提出了一种新颖的主动学习策略，以帮助目标域中的知识转移，有效域适应。我们从观察开始，即当训练（源）和测试（目标）数据来自不同的分布时，基于能量的模型表现出自由能量偏差。灵感来自这种固有的机制，我们经验揭示了一种简单而有效的能源 - 基于能量的采样策略揭示了比需要特定架构或距离计算的现有方法的最有价值的目标样本。我们的算法，基于能量的活动域适应（EADA），查询逻辑数据组，它将域特征和实例不确定性结合到每个选择回合中。同时，通过通过正则化术语对准源域周围的目标数据紧凑的自由能，可以隐含地减少域间隙。通过广泛的实验，我们表明EADA在众所周知的具有挑战性的基准上超越了最先进的方法，具有实质性的改进，使其成为开放世界中的一个有用的选择。代码可在https://github.com/bit-da/eada获得。

无监督的域适应（UDA）旨在将知识从标记的源域传输到未标记的目标域。大多数现有的UDA方法通过学习域 - 不变的表示和在两个域中共享一个分类器来实现知识传输。但是，忽略与任务相关的域特定信息，并强制统一的分类器以适合两个域将限制每个域中的特征表达性。在本文中，通过观察到具有可比参数的变压器架构可以产生比CNN对应的更可转换的表示，我们提出了一个双赢的变压器框架（WINTR），它分别探讨了每个域的特定于域的知识，而同时交互式跨域知识。具体而言，我们使用变压器中的两个单独的分类令牌学习两个不同的映射，以及每个特定于域的分类器的设计。跨域知识通过源引导标签改进和与源或目标的单侧特征对齐传输，这保持了特定于域的信息的完整性。三个基准数据集的广泛实验表明，我们的方法优于最先进的UDA方法，验证利用域特定和不变性的有效性

自我训练具有极大的促进域自适应语义分割，它迭代地在目标域上生成伪标签并删除网络。然而，由于现实分割数据集是高度不平衡的，因此目标伪标签通常偏置到多数类并且基本上嘈杂，导致出错和次优模型。为了解决这个问题，我们提出了一个基于区域的主动学习方法，用于在域移位下进行语义分割，旨在自动查询要标记的图像区域的小分区，同时最大化分割性能。我们的算法，通过区域杂质和预测不确定性（AL-RIPU）的主动学习，介绍了一种新的采集策略，其特征在于图像区域的空间邻接以及预测置信度。我们表明，所提出的基于地区的选择策略比基于图像或基于点的对应物更有效地使用有限预算。同时，我们在源图像上强制在像素和其最近邻居之间的局部预测一致性。此外，我们制定了负面学习损失，以提高目标领域的鉴别表现。广泛的实验表明，我们的方法只需要极少的注释几乎达到监督性能，并且大大优于最先进的方法。

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.

Deep learning has been widely used in the perception (e.g., 3D object detection) of intelligent vehicle driving. Due to the beneficial Vehicle-to-Vehicle (V2V) communication, the deep learning based features from other agents can be shared to the ego vehicle so as to improve the perception of the ego vehicle. It is named as Cooperative Perception in the V2V research, whose algorithms have been dramatically advanced recently. However, all the existing cooperative perception algorithms assume the ideal V2V communication without considering the possible lossy shared features because of the Lossy Communication (LC) which is common in the complex real-world driving scenarios. In this paper, we first study the side effect (e.g., detection performance drop) by the lossy communication in the V2V Cooperative Perception, and then we propose a novel intermediate LC-aware feature fusion method to relieve the side effect of lossy communication by a LC-aware Repair Network (LCRN) and enhance the interaction between the ego vehicle and other vehicles by a specially designed V2V Attention Module (V2VAM) including intra-vehicle attention of ego vehicle and uncertainty-aware inter-vehicle attention. The extensive experiment on the public cooperative perception dataset OPV2V (based on digital-twin CARLA simulator) demonstrates that the proposed method is quite effective for the cooperative point cloud based 3D object detection under lossy V2V communication.