Image super-resolution is a common task on mobile and IoT devices, where one often needs to upscale and enhance low-resolution images and video frames. While numerous solutions have been proposed for this problem in the past, they are usually not compatible with low-power mobile NPUs having many computational and memory constraints. In this Mobile AI challenge, we address this problem and propose the participants to design an efficient quantized image super-resolution solution that can demonstrate a real-time performance on mobile NPUs. The participants were provided with the DIV2K dataset and trained INT8 models to do a high-quality 3X image upscaling. The runtime of all models was evaluated on the Synaptics VS680 Smart Home board with a dedicated edge NPU capable of accelerating quantized neural networks. All proposed solutions are fully compatible with the above NPU, demonstrating an up to 60 FPS rate when reconstructing Full HD resolution images. A detailed description of all models developed in the challenge is provided in this paper.

基于深度学习的单图像超分辨率（SISR）方法引起了人们的关注，并在现代高级GPU上取得了巨大的成功。但是，大多数最先进的方法都需要大量参数，记忆和计算资源，这些参数通常会显示在当前移动设备CPU/NPU上时显示出较低的推理时间。在本文中，我们提出了一个简单的普通卷积网络，该网络具有快速最近的卷积模块（NCNET），该模块对NPU友好，可以实时执行可靠的超级分辨率。提出的最近的卷积具有与最近的UP采样相同的性能，但更快，更适合Android NNAPI。我们的模型可以很容易地在具有8位量化的移动设备上部署，并且与所有主要的移动AI加速器完全兼容。此外，我们对移动设备上的不同张量操作进行了全面的实验，以说明网络体系结构的效率。我们的NCNET在DIV2K 3X数据集上进行了训练和验证，并且与其他有效的SR方法的比较表明，NCNET可以实现高保真SR结果，同时使用更少的推理时间。我们的代码和预估计的模型可在\ url {https://github.com/algolzw/ncnet}上公开获得。

肝脏的准确细分是诊断疾病的先决条件。自动分割是计算机辅助检测和肝病诊断的重要应用。近年来，医学图像的自动化处理已经取得了突破。然而，腹部扫描CT图像的低对比度和肝脏形态的复杂性使得精确的自动分割具有挑战性。在本文中，我们提出了RA V-NET，这是基于U-Net的改进的医学图像自动分割模型。它有以下三个主要创新。建议Cofres模块（复合原始功能剩余模块）。通过更复杂的卷积层和跳过连接，使其获得更高级别的图像特征提取功能并防止梯度消失或爆炸。建议AR模块（注意恢复模块）以减少模型的计算工作。另外，通过调整通道和LSTM卷积来感测编码和解码模块的数据像素之间的空间特征。最后，有效地保留了图像特征。介绍了CA模块（通道注意模块），用于提取具有依赖性的相关通道，并通过矩阵点产品加强它们，同时在没有依赖性的情况下削弱无关的通道。达到关注的目的。 LSTM卷积和CA模块提供的注意机制是强证神经网络性能的保证。 U-Net网络的准确性：0.9862，精确度：0.9118，DSC：0.8547，JSC：0.82。 RA V-NET的评估指标，精度：0.9968，精确度：0.9597，DSC：0.9654，JSC：0.9414。分割效果的最代表性度量是DSC，其在U-NET上改善0.1107，JSC改善0.1214。

现在，推荐系统已经变得繁荣，旨在通过学习嵌入来预测用户对项目的潜在兴趣。图形神经网络的最新进展〜（GNNS）还提供带有强大备份的推荐系统，从用户项图中学习嵌入。但是，由于数据收集困难，仅利用用户项交互遭受冷启动问题。因此，目前的努力建议将社交信息与用户项目相互作用融合以缓解它，这是社会推荐问题。现有工作使用GNNS同时聚合两个社交链接和用户项交互。但是，它们都需要集中存储的社交链接和用户的互动，从而导致隐私问题。此外，根据严格的隐私保护，在一般数据保护规则下，将来可能不可行的数据存储可能是不可行的，敦促分散的社会建议框架。为此，我们设计了一个小说框架\ textbf {fe} delated \ textbf {so} cial推荐与\ textbf {g} raph神经网络（fesog）。首先，FeSog采用关系的关注和聚集来处理异质性。其次，Fesog Infers使用本地数据来保留个性化的用户嵌入。最后但并非最不重要的是，所提出的模型采用伪标签技术，其中包含项目采样，以保护隐私和增强培训。三个现实世界数据集的广泛实验可以证明FeSog在完成社会建议和隐私保护方面的有效性。我们是为我们所知，为社会建议提供联邦学习框架的第一项工作。

人工智能（AI）为简化Covid-19诊断提供了有前景的替代。然而，涉及周围的安全和可信度的担忧阻碍了大规模代表性的医学数据，对临床实践中训练广泛的模型造成了相当大的挑战。为了解决这个问题，我们启动了统一的CT-Covid AI诊断计划（UCADI），其中AI模型可以在没有数据共享的联合学习框架（FL）下在每个主机机构下分发和独立地在没有数据共享的情况下在每个主机机构上执行。在这里，我们认为我们的FL模型通过大的产量（中国测试敏感性/特异性：0.973 / 0.951，英国：0.730 / 0.942），与专业放射科医师的面板实现可比性表现。我们进一步评估了持有的模型（从另外两家医院收集，留出FL）和异构（用造影材料获取）数据，提供了模型所做的决策的视觉解释，并分析了模型之间的权衡联邦培训过程中的性能和沟通成本。我们的研究基于来自位于中国和英国的23家医院的3,336名患者的9,573次胸部计算断层扫描扫描（CTS）。统称，我们的工作提出了利用联邦学习的潜在保留了数字健康的前景。

Remote sensing of the Earth's surface water is critical in a wide range of environmental studies, from evaluating the societal impacts of seasonal droughts and floods to the large-scale implications of climate change. Consequently, a large literature exists on the classification of water from satellite imagery. Yet, previous methods have been limited by 1) the spatial resolution of public satellite imagery, 2) classification schemes that operate at the pixel level, and 3) the need for multiple spectral bands. We advance the state-of-the-art by 1) using commercial imagery with panchromatic and multispectral resolutions of 30 cm and 1.2 m, respectively, 2) developing multiple fully convolutional neural networks (FCN) that can learn the morphological features of water bodies in addition to their spectral properties, and 3) FCN that can classify water even from panchromatic imagery. This study focuses on rivers in the Arctic, using images from the Quickbird, WorldView, and GeoEye satellites. Because no training data are available at such high resolutions, we construct those manually. First, we use the RGB, and NIR bands of the 8-band multispectral sensors. Those trained models all achieve excellent precision and recall over 90% on validation data, aided by on-the-fly preprocessing of the training data specific to satellite imagery. In a novel approach, we then use results from the multispectral model to generate training data for FCN that only require panchromatic imagery, of which considerably more is available. Despite the smaller feature space, these models still achieve a precision and recall of over 85%. We provide our open-source codes and trained model parameters to the remote sensing community, which paves the way to a wide range of environmental hydrology applications at vastly superior accuracies and 2 orders of magnitude higher spatial resolution than previously possible.

We present NusaCrowd, a collaborative initiative to collect and unite existing resources for Indonesian languages, including opening access to previously non-public resources. Through this initiative, we have has brought together 137 datasets and 117 standardized data loaders. The quality of the datasets has been assessed manually and automatically, and their effectiveness has been demonstrated in multiple experiments. NusaCrowd's data collection enables the creation of the first zero-shot benchmarks for natural language understanding and generation in Indonesian and its local languages. Furthermore, NusaCrowd brings the creation of the first multilingual automatic speech recognition benchmark in Indonesian and its local languages. Our work is intended to help advance natural language processing research in under-represented languages.

Reference-based Super-Resolution (Ref-SR) has recently emerged as a promising paradigm to enhance a low-resolution (LR) input image or video by introducing an additional high-resolution (HR) reference image. Existing Ref-SR methods mostly rely on implicit correspondence matching to borrow HR textures from reference images to compensate for the information loss in input images. However, performing local transfer is difficult because of two gaps between input and reference images: the transformation gap (e.g., scale and rotation) and the resolution gap (e.g., HR and LR). To tackle these challenges, we propose C2-Matching in this work, which performs explicit robust matching crossing transformation and resolution. 1) To bridge the transformation gap, we propose a contrastive correspondence network, which learns transformation-robust correspondences using augmented views of the input image. 2) To address the resolution gap, we adopt teacher-student correlation distillation, which distills knowledge from the easier HR-HR matching to guide the more ambiguous LR-HR matching. 3) Finally, we design a dynamic aggregation module to address the potential misalignment issue between input images and reference images. In addition, to faithfully evaluate the performance of Reference-based Image Super-Resolution under a realistic setting, we contribute the Webly-Referenced SR (WR-SR) dataset, mimicking the practical usage scenario. We also extend C2-Matching to Reference-based Video Super-Resolution task, where an image taken in a similar scene serves as the HR reference image. Extensive experiments demonstrate that our proposed C2-Matching significantly outperforms state of the arts on the standard CUFED5 benchmark and also boosts the performance of video SR by incorporating the C2-Matching component into Video SR pipelines.

In recent years, vision-centric perception has flourished in various autonomous driving tasks, including 3D detection, semantic map construction, motion forecasting, and depth estimation. Nevertheless, the latency of vision-centric approaches is too high for practical deployment (e.g., most camera-based 3D detectors have a runtime greater than 300ms). To bridge the gap between ideal research and real-world applications, it is necessary to quantify the trade-off between performance and efficiency. Traditionally, autonomous-driving perception benchmarks perform the offline evaluation, neglecting the inference time delay. To mitigate the problem, we propose the Autonomous-driving StreAming Perception (ASAP) benchmark, which is the first benchmark to evaluate the online performance of vision-centric perception in autonomous driving. On the basis of the 2Hz annotated nuScenes dataset, we first propose an annotation-extending pipeline to generate high-frame-rate labels for the 12Hz raw images. Referring to the practical deployment, the Streaming Perception Under constRained-computation (SPUR) evaluation protocol is further constructed, where the 12Hz inputs are utilized for streaming evaluation under the constraints of different computational resources. In the ASAP benchmark, comprehensive experiment results reveal that the model rank alters under different constraints, suggesting that the model latency and computation budget should be considered as design choices to optimize the practical deployment. To facilitate further research, we establish baselines for camera-based streaming 3D detection, which consistently enhance the streaming performance across various hardware. ASAP project page: https://github.com/JeffWang987/ASAP.

In a high dimensional linear predictive regression where the number of potential predictors can be larger than the sample size, we consider using LASSO, a popular L1-penalized regression method, to estimate the sparse coefficients when many unit root regressors are present. Consistency of LASSO relies on two building blocks: the deviation bound of the cross product of the regressors and the error term, and the restricted eigenvalue of the Gram matrix of the regressors. In our setting where unit root regressors are driven by temporal dependent non-Gaussian innovations, we establish original probabilistic bounds for these two building blocks. The bounds imply that the rates of convergence of LASSO are different from those in the familiar cross sectional case. In practical applications given a mixture of stationary and nonstationary predictors, asymptotic guarantee of LASSO is preserved if all predictors are scale-standardized. In an empirical example of forecasting the unemployment rate with many macroeconomic time series, strong performance is delivered by LASSO when the initial specification is guided by macroeconomic domain expertise.