Sockeye 3是神经机器翻译（NMT）的Mockeye工具包的最新版本。现在，基于Pytorch，Sockeye 3提供了更快的模型实现和更高级的功能，并具有进一步的简化代码库。这可以通过更快的迭代，对更强大，更快的模型进行有效的培训以及快速从研究转移到生产的新想法的灵活性，从而实现更广泛的实验。当运行可比较的型号时，Sockeye 3的速度比GPU上的其他Pytorch实现快126％，在CPU上的实现速度高达292％。Sockeye 3是根据Apache 2.0许可发布的开源软件。

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.

The security of artificial intelligence (AI) is an important research area towards safe, reliable, and trustworthy AI systems. To accelerate the research on AI security, the Artificial Intelligence Security Competition (AISC) was organized by the Zhongguancun Laboratory, China Industrial Control Systems Cyber Emergency Response Team, Institute for Artificial Intelligence, Tsinghua University, and RealAI as part of the Zhongguancun International Frontier Technology Innovation Competition (https://www.zgc-aisc.com/en). The competition consists of three tracks, including Deepfake Security Competition, Autonomous Driving Security Competition, and Face Recognition Security Competition. This report will introduce the competition rules of these three tracks and the solutions of top-ranking teams in each track.

Transformer-based language models have become the standard approach to solving natural language processing tasks. However, industry adoption usually requires the maximum throughput to comply with certain latency constraints that prevents Transformer models from being used in production. To address this gap, model compression techniques such as quantization and pruning may be used to improve inference efficiency. However, these compression techniques require specialized software to apply and deploy at scale. In this work, we propose a new pipeline for creating and running Fast Transformer models on CPUs, utilizing hardware-aware pruning, knowledge distillation, quantization, and our own Transformer inference runtime engine with optimized kernels for sparse and quantized operators. We demonstrate the efficiency of our pipeline by creating a Fast DistilBERT model showing minimal accuracy loss on the question-answering SQuADv1.1 benchmark, and throughput results under typical production constraints and environments. Our results outperform existing state-of-the-art Neural Magic's DeepSparse runtime performance by up to 50% and up to 4.1x performance speedup over ONNX Runtime. Source code is publicly available at https://github.com/intel/intel-extension-for-transformers.

胸部计算机断层扫描的气道分割在肺部疾病诊断中起着至关重要的作用。与手动分割相比，基于U-NET体系结构的计算机辅助气道分割更有效，更准确。在本文中，我们采用了由骰子损失功能训练的U $^2 $ -NET，以基于ATM'22提供的299次培训CT扫描，对多站点CT扫描的气道树进行建模。从训练中将派生的显着性概率图应用于验证数据以提取相应的气道树。该观察结果表明，大多数分割的气道树从准确性和连通性的角度表现出色。将诸如非航空区域标签和去除之类的改进应用于某些获得的气道树模型，以显示二进制结果的最大组成部分。

我们提出了一个基于串联弹性执行器（SEA）的平行按摩机器人，提供统一的力量控制方法。首先，建立了运动和静态力模型，以获得相应的控制变量。然后，提出了一种新型的力位控制策略，以在不需要机器人动力学模型的情况下分别控制沿表面正常方向的力位和另一个两方向位移。为了评估其性能，我们实施了一系列机器人按摩实验。结果表明，所提出的按摩操纵器可以成功实现按摩任务的所需力和运动模式，从而达到高得分用户体验。

本文回顾了AIM 2022上压缩图像和视频超级分辨率的挑战。这项挑战包括两条曲目。轨道1的目标是压缩图像的超分辨率，轨迹〜2靶向压缩视频的超分辨率。在轨道1中，我们使用流行的数据集DIV2K作为培训，验证和测试集。在轨道2中，我们提出了LDV 3.0数据集，其中包含365个视频，包括LDV 2.0数据集（335个视频）和30个其他视频。在这一挑战中，有12支球队和2支球队分别提交了赛道1和赛道2的最终结果。所提出的方法和解决方案衡量了压缩图像和视频上超分辨率的最先进。提出的LDV 3.0数据集可在https://github.com/renyang-home/ldv_dataset上找到。此挑战的首页是在https://github.com/renyang-home/aim22_compresssr。

低光环境对强大的无人驾驶汽车（UAV）跟踪也构成了巨大的挑战，即使使用最新的（SOTA）跟踪器，由于潜在的图像特征在不利的光条件下很难提取。此外，由于可见性较低，人类监视器的准确在线选择也极为难以在地面控制站中初始化无人机跟踪。为了解决这些问题，这项工作提出了一个新颖的增强剂，即凸线网，以点燃人类操作员和无人机跟踪器的潜在对象。通过采用变压器，LightlightNet可以根据全局特征调整增强参数，因此可以适应照明变化。引入了像素级范围掩模，以使光明网络更加专注于没有光源的跟踪对象和区域的增强。此外，建立了一种软截断机制，以防止背景噪声被误认为关键特征。对图像增强基准测试的评估表明，光明网络在促进人类感知方面具有优势。公共Uavdark135基准进行的实验表明，HightlightNet比其他SOTA低光增强剂更适合无人机跟踪任务。此外，在典型的无人机平台上进行的现实世界测试验证了HightlightNet在夜间航空跟踪相关应用中的实用性和效率。代码和演示视频可在https://github.com/vision4robotics/highlightnet上找到。

蒙版图像建模（MIM）通过恢复损坏的图像补丁，在自我监督的表示学习中表现出了令人印象深刻的结果。但是，大多数方法仍在低级图像像素上运行，这阻碍了对表示模型的高级语义的开发。在这项研究中，我们建议将富含语义的视觉令牌用作掩盖预测的重建目标，从而提供了一种系统的方式来促进MIM从像素级到语义级别。具体而言，我们引入了矢量定量的知识蒸馏以训练令牌仪，该蒸馏器将连续的语义空间离散为紧凑的代码。然后，我们通过预测掩盖图像贴片的原始视觉令牌来预处理变压器。此外，我们鼓励该模型将补丁信息明确汇总到全局图像表示中，该图像表示该设施线性探测。图像分类和语义分割的实验表明，我们的方法优于所有方法比较MIM方法。在ImagEnet-1K（224尺寸）上，基本大小的BEIT V2可实现85.5％的top-1精度，用于微调和80.1％的线性探测的TOP-1精度。大尺寸的BEIT V2获得了ImagEnet-1K（224尺寸）微调的最高1个TOP-1精度，用于语义分割的ADE20K上获得了56.7％MIOU。代码和预估计的模型可在https://aka.ms/beit上找到。

机器学习中的许多基本问题可以通过convex程序\ [\ min _ {\ theta \ in r^d} \ sum_ {i = 1}^{n} f_ {i}（\ theta），\]每个$ f_i $都是一个凸，Lipschitz函数在$ \ theta $的$ d_i $坐标的子集中支持。以随机梯度下降为例，解决此问题的一种常见方法涉及在每次迭代时对一个$ f_i $术语进行采样以取得进展。这种方法至关重要地依赖于$ f_i $的均匀性概念，该概念正式通过其状况编号捕获。在这项工作中，我们给出了一种将上述凸公式最小化为$ \ epsilon $ -Accuracy in $ \ widetilde {o}（\ sum_ {i = 1}^n d_i \ log（1 /\ epsilon）$计算，没有关于条件号的假设。以前的最佳算法独立于条件编号是标准切割平面方法，它需要$ o（nd \ log（1/\ epsilon））$渐变计算。作为推论，我们改善了Axiotis等人的评估甲骨文的复杂性，可分解性下的最小化。 （ICML 2021）。我们的主要技术贡献是一种自适应程序，可以通过切割平面和内点方法的新型组合在每次迭代中选择$ f_i $项。