Unlike traditional distributed machine learning, federated learning stores data locally for training and then aggregates the models on the server, which solves the data security problem that may arise in traditional distributed machine learning. However, during the training process, the transmission of model parameters can impose a significant load on the network bandwidth. It has been pointed out that the vast majority of model parameters are redundant during model parameter transmission. In this paper, we explore the data distribution law of selected partial model parameters on this basis, and propose a deep hierarchical quantization compression algorithm, which further compresses the model and reduces the network load brought by data transmission through the hierarchical quantization of model parameters. And we adopt a dynamic sampling strategy for the selection of clients to accelerate the convergence of the model. Experimental results on different public datasets demonstrate the effectiveness of our algorithm.

Semantic segmentation of UAV aerial remote sensing images provides a more efficient and convenient surveying and mapping method for traditional surveying and mapping. In order to make the model lightweight and improve a certain accuracy, this research developed a new lightweight and efficient network for the extraction of ground features from UAV aerial remote sensing images, called LDMCNet. Meanwhile, this research develops a powerful lightweight backbone network for the proposed semantic segmentation model. It is called LDCNet, and it is hoped that it can become the backbone network of a new generation of lightweight semantic segmentation algorithms. The proposed model uses dual multi-scale context modules, namely the Atrous Space Pyramid Pooling module (ASPP) and the Object Context Representation module (OCR). In addition, this research constructs a private dataset for semantic segmentation of aerial remote sensing images from drones. This data set contains 2431 training sets, 945 validation sets, and 475 test sets. The proposed model performs well on this dataset, with only 1.4M parameters and 5.48G floating-point operations (FLOPs), achieving an average intersection-over-union ratio (mIoU) of 71.12%. 7.88% higher than the baseline model. In order to verify the effectiveness of the proposed model, training on the public datasets "LoveDA" and "CITY-OSM" also achieved excellent results, achieving mIoU of 65.27% and 74.39%, respectively.

We study a challenging task, conditional human motion generation, which produces plausible human motion sequences according to various conditional inputs, such as action classes or textual descriptors. Since human motions are highly diverse and have a property of quite different distribution from conditional modalities, such as textual descriptors in natural languages, it is hard to learn a probabilistic mapping from the desired conditional modality to the human motion sequences. Besides, the raw motion data from the motion capture system might be redundant in sequences and contain noises; directly modeling the joint distribution over the raw motion sequences and conditional modalities would need a heavy computational overhead and might result in artifacts introduced by the captured noises. To learn a better representation of the various human motion sequences, we first design a powerful Variational AutoEncoder (VAE) and arrive at a representative and low-dimensional latent code for a human motion sequence. Then, instead of using a diffusion model to establish the connections between the raw motion sequences and the conditional inputs, we perform a diffusion process on the motion latent space. Our proposed Motion Latent-based Diffusion model (MLD) could produce vivid motion sequences conforming to the given conditional inputs and substantially reduce the computational overhead in both the training and inference stages. Extensive experiments on various human motion generation tasks demonstrate that our MLD achieves significant improvements over the state-of-the-art methods among extensive human motion generation tasks, with two orders of magnitude faster than previous diffusion models on raw motion sequences.

The image captioning task is typically realized by an auto-regressive method that decodes the text tokens one by one. We present a diffusion-based captioning model, dubbed the name DDCap, to allow more decoding flexibility. Unlike image generation, where the output is continuous and redundant with a fixed length, texts in image captions are categorical and short with varied lengths. Therefore, naively applying the discrete diffusion model to text decoding does not work well, as shown in our experiments. To address the performance gap, we propose several key techniques including best-first inference, concentrated attention mask, text length prediction, and image-free training. On COCO without additional caption pre-training, it achieves a CIDEr score of 117.8, which is +5.0 higher than the auto-regressive baseline with the same architecture in the controlled setting. It also performs +26.8 higher CIDEr score than the auto-regressive baseline (230.3 v.s.203.5) on a caption infilling task. With 4M vision-language pre-training images and the base-sized model, we reach a CIDEr score of 125.1 on COCO, which is competitive to the best well-developed auto-regressive frameworks. The code is available at https://github.com/buxiangzhiren/DDCap.

Radar, the only sensor that could provide reliable perception capability in all weather conditions at an affordable cost, has been widely accepted as a key supplement to camera and LiDAR in modern advanced driver assistance systems (ADAS) and autonomous driving systems. Recent state-of-the-art works reveal that fusion of radar and LiDAR can lead to robust detection in adverse weather, such as fog. However, these methods still suffer from low accuracy of bounding box estimations. This paper proposes a bird's-eye view (BEV) fusion learning for an anchor box-free object detection system, which uses the feature derived from the radar range-azimuth heatmap and the LiDAR point cloud to estimate the possible objects. Different label assignment strategies have been designed to facilitate the consistency between the classification of foreground or background anchor points and the corresponding bounding box regressions. Furthermore, the performance of the proposed object detector can be further enhanced by employing a novel interactive transformer module. We demonstrated the superior performance of the proposed methods in this paper using the recently published Oxford Radar RobotCar (ORR) dataset. We showed that the accuracy of our system significantly outperforms the other state-of-the-art methods by a large margin.

Various depth estimation models are now widely used on many mobile and IoT devices for image segmentation, bokeh effect rendering, object tracking and many other mobile tasks. Thus, it is very crucial to have efficient and accurate depth estimation models that can run fast on low-power mobile chipsets. In this Mobile AI challenge, the target was to develop deep learning-based single image depth estimation solutions that can show a real-time performance on IoT platforms and smartphones. For this, the participants used a large-scale RGB-to-depth dataset that was collected with the ZED stereo camera capable to generated depth maps for objects located at up to 50 meters. The runtime of all models was evaluated on the Raspberry Pi 4 platform, where the developed solutions were able to generate VGA resolution depth maps at up to 27 FPS while achieving high fidelity results. All models developed in the challenge are also compatible with any Android or Linux-based mobile devices, their detailed description is provided in this paper.

通过利用大型内核分解和注意机制，卷积神经网络（CNN）可以在许多高级计算机视觉任务中与基于变压器的方法竞争。但是，由于远程建模的优势，具有自我注意力的变压器仍然主导着低级视野，包括超分辨率任务。在本文中，我们提出了一个基于CNN的多尺度注意网络（MAN），该网络由多尺度的大内核注意力（MLKA）和一个封闭式的空间注意单元（GSAU）组成，以提高卷积SR网络的性能。在我们的MLKA中，我们使用多尺度和栅极方案纠正LKA，以在各种粒度水平上获得丰富的注意图，从而共同汇总了全局和局部信息，并避免了潜在的阻塞伪像。在GSAU中，我们集成了栅极机制和空间注意力，以消除不必要的线性层和汇总信息丰富的空间环境。为了确认我们的设计的有效性，我们通过简单地堆叠不同数量的MLKA和GSAU来评估具有多种复杂性的人。实验结果表明，我们的人可以在最先进的绩效和计算之间实现各种权衡。代码可从https://github.com/icandle/man获得。

从单眼视频中进行的3D人姿势估计最近看到了显着改善。但是，大多数最先进的方法都是基于运动学的，它容易出现具有明显伪影的物理上不可信的运动。当前基于动态的方法可以预测物理上合理的运动，但仅限于具有静态相机视图的简单场景。在这项工作中，我们介绍了D＆D（从动态相机中学习人类动力学），该法律利用物理定律使用移动的摄像机从野外视频中重建3D人类运动。 D＆D引入了惯性力控制（IFC），以考虑动态摄像机的惯性力来解释非惯性局部框架中的3D人运动。为了学习有限注释的接地接触，我们开发了概率接触扭矩（PCT），该概率是通过与接触概率的可区分抽样计算的，并用于生成运动。接触状态可以通过鼓励模型产生正确的动作来弱监督。此外，我们提出了一个细心的PD控制器，该控制器使用时间信息来调整目标姿势状态，以获得平稳而准确的姿势控制。我们的方法完全是基于神经的，并且在物理引擎中没有离线优化或模拟的情况下运行。大规模3D人体运动基准的实验证明了D＆D的有效性，在该基于最新的运动学基于动力学和基于动力学的方法的情况下，我们表现出卓越的性能。代码可从https://github.com/jeffsjtu/dnd获得

具有高分辨率（HR）的磁共振成像（MRI）提供了更详细的信息，以进行准确的诊断和定量图像分析。尽管取得了重大进展，但大多数现有的医学图像重建网络都有两个缺陷：1）所有这些缺陷都是在黑盒原理中设计的，因此缺乏足够的解释性并进一步限制其实际应用。可解释的神经网络模型引起了重大兴趣，因为它们在处理医学图像时增强了临床实践所需的可信赖性。 2）大多数现有的SR重建方法仅使用单个对比度或使用简单的多对比度融合机制，从而忽略了对SR改进至关重要的不同对比度之间的复杂关系。为了解决这些问题，在本文中，提出了一种新颖的模型引导的可解释的深层展开网络（MGDUN），用于医学图像SR重建。模型引导的图像SR重建方法求解手动设计的目标函数以重建HR MRI。我们通过将MRI观察矩阵和显式多对比度关系矩阵考虑到末端到端优化期间，将迭代的MGDUN算法展示为新型模型引导的深层展开网络。多对比度IXI数据集和Brats 2019数据集进行了广泛的实验，证明了我们提出的模型的优势。

本文提出了一种新颖的统一特征优化（UFO）范式，用于训练和在现实世界和大规模场景下进行深层模型，这需要集合多个AI功能。不明飞行物的目标是通过对所有任务进行大规模预修。与众所周知的基础模型相比，UFO具有两个不同的重点，即相对较小的模型大小，没有适应性成本：1）UFO以多任务学习方式将广泛的任务挤入中等尺寸的统一模型中并在转移到下游任务时进一步修剪模型大小。 2）不明飞行物不强调转移到新任务。相反，它旨在使修剪模型专门用于一个或多个已经看到的任务。有了这两个特征，UFO为灵活的部署提供了极大的便利，同时保持了大规模预处理的好处。 UFO的一个关键优点是修剪过程不仅可以减少模型的大小和推理消耗，而且还提高了某些任务的准确性。具体而言，UFO考虑了多任务培训，并对统一模型产生了两倍的影响：一些密切相关的任务具有相互利益，而某些任务相互冲突。不明飞行物设法通过新颖的网络体系结构搜索（NAS）方法来减少冲突并保留相互利益。对各种深度表示学习任务（即面部识别，人重新识别，车辆重新识别和产品检索）的实验表明，从UFO中修剪的模型比单件任务训练的对应物更高，但却具有更高的准确性较小的型号大小，验证不明飞行物的概念。此外，UFO还支持发布170亿个参数计算机视觉（CV）基础模型，该模型是该行业中最大的CV模型。