The modern dynamic and heterogeneous network brings differential environments with respective state transition probability to agents, which leads to the local strategy trap problem of traditional federated reinforcement learning (FRL) based network optimization algorithm. To solve this problem, we propose a novel Differentiated Federated Reinforcement Learning (DFRL), which evolves the global policy model integration and local inference with the global policy model in traditional FRL to a collaborative learning process with parallel global trends learning and differential local policy model learning. In the DFRL, the local policy learning model is adaptively updated with the global trends model and local environment and achieves better differentiated adaptation. We evaluate the outperformance of the proposal compared with the state-of-the-art FRL in a classical CartPole game with heterogeneous environments. Furthermore, we implement the proposal in the heterogeneous Space-air-ground Integrated Network (SAGIN) for the classical traffic offloading problem in network. The simulation result shows that the proposal shows better global performance and fairness than baselines in terms of throughput, delay, and packet drop rate.

由于自我批判性和歧义，了解动态的手动运动和动态动作是一项基本而又具有挑战性的任务。为了解决遮挡和歧义，我们开发了一个基于变压器的框架来利用时间信息以进行稳健的估计。注意到手部姿势估计和动作识别之间的不同时间粒度和语义相关性，我们建立了一个网络层次结构，其中有两个级联变压器编码器，其中第一个利用了短期的时间cue进行手姿势估算，而后者则每次聚集物，后者每次聚集体 - 帧姿势和对象信息在更长的时间范围内识别动作。我们的方法在两个第一人称手动作基准（即FPHA和H2O）上取得了竞争成果。广泛的消融研究验证了我们的设计选择。我们将开放源代码和数据以促进未来的研究。

尽管视觉变压器模型的令人印象深刻的表示能力，但目前的轻型视觉变压器模型仍然遭受当地地区的不一致和不正确的预测。我们怀疑他们的自我关注机制的力量在较浅和较薄的网络中受到限制。我们提出Lite Vision变压器（LVT），一种新型轻型变压器网络，具有两个增强的自我关注机制，可以改善移动部署的模型性能。对于低级功能，我们介绍了卷积自我关注（CSA）。与以前的合并卷积和自我关注的方法不同，CSA将局部自我关注引入到大小3x3内核内的卷积中，以丰富LVT第一阶段的低级功能。对于高级功能，我们提出了在计算相似性图和递归机制时利用多尺度上下文的递归的自我关注，以增加具有边际额外参数成本的表示能力。 Imagenet识别，ADE20K语义分割和CoCo Panoptic分割对LVT的优越性。代码公开可用。

当由于雨或雪等外部条件而突然牵引时，漂移控制对于自主车辆的安全性是显着的。由于存在显着的侧滑和轮胎几乎完整的饱和度，这是一个具有挑战性的控制问题。在本文中，我们专注于在固定或移动中心的圆形路径之后控制漂移行动，可能会导致轮胎地面互动的变化，这是漂移爱好者的常见培训任务，因此可以用作性能的基准漂移控制。为了实现上述任务，我们提出了一种新颖的等级控制架构，其解耦了轨迹的曲率和中心控制。特别地，外环通过调谐目标曲率来稳定中心，并且内环使用由$ \ mathcal {l} _1 $自适应组件增强的前馈/反馈控制器跟踪曲率。分层体系结构是灵活的，因为内部环路是任务 - 不可行的和适应轮胎道路交互的变化，这允许外部环路独立于低电平动态设计，打开结合复杂的规划算法的可能性。我们在仿真平台以及1/10级无线电控制〜（RC）汽车上实施我们的控制策略，仿真和实验结果都说明了我们在实现上述漂移机动任务方案集中的策略的有效性。

RGB图像的刚性对象的可伸缩6D构成估计旨在处理多个对象并推广到新物体。我们建立在一个著名的自动编码框架的基础上，以应对对象对称性和缺乏标记的训练数据，我们通过将自动编码器的潜在表示形状分解为形状并构成子空间来实现可伸缩性。潜在形状空间通过对比度度量学习模型不同对象的相似性，并将潜在姿势代码与旋转检索的规范旋转进行比较。由于不同的对象对称会诱导不一致的潜在姿势空间，因此我们用规范旋转重新输入形状表示，以生成形状依赖的姿势代码簿以进行旋转检索。我们在两个基准上显示了最新的性能，其中包含无类别和每日对象的无纹理CAD对象，并通过扩展到跨类别的每日对象的更具挑战性的设置，进一步证明了可扩展性。

Current practice in interpretable machine learning often focuses on explaining the final model trained from data, e.g., by using the Shapley additive explanations (SHAP) method. The recently developed Shapley variable importance cloud (ShapleyVIC) extends the current practice to a group of "nearly optimal models" to provide comprehensive and robust variable importance assessments, with estimated uncertainty intervals for a more complete understanding of variable contributions to predictions. ShapleyVIC was initially developed for applications with traditional regression models, and the benefits of ShapleyVIC inference have been demonstrated in real-life prediction tasks using the logistic regression model. However, as a model-agnostic approach, ShapleyVIC application is not limited to such scenarios. In this work, we extend ShapleyVIC implementation for machine learning models to enable wider applications, and propose it as a useful complement to the current SHAP analysis to enable more trustworthy applications of these black-box models.

We present the development of a semi-supervised regression method using variational autoencoders (VAE), which is customized for use in soft sensing applications. We motivate the use of semi-supervised learning considering the fact that process quality variables are not collected at the same frequency as other process variables leading to many unlabelled records in operational datasets. These unlabelled records are not possible to use for training quality variable predictions based on supervised learning methods. Use of VAEs for unsupervised learning is well established and recently they were used for regression applications based on variational inference procedures. We extend this approach of supervised VAEs for regression (SVAER) to make it learn from unlabelled data leading to semi-supervised VAEs for regression (SSVAER), then we make further modifications to their architecture using additional regularization components to make SSVAER well suited for learning from both labelled and unlabelled process data. The probabilistic regressor resulting from the variational approach makes it possible to estimate the variance of the predictions simultaneously, which provides an uncertainty quantification along with the generated predictions. We provide an extensive comparative study of SSVAER with other publicly available semi-supervised and supervised learning methods on two benchmark problems using fixed-size datasets, where we vary the percentage of labelled data available for training. In these experiments, SSVAER achieves the lowest test errors in 11 of the 20 studied cases, compared to other methods where the second best gets 4 lowest test errors out of the 20.

Dense pose estimation is a dense 3D prediction task for instance-level human analysis, aiming to map human pixels from an RGB image to a 3D surface of the human body. Due to a large amount of surface point regression, the training process appears to be easy to collapse compared to other region-based human instance analyzing tasks. By analyzing the loss formulation of the existing dense pose estimation model, we introduce a novel point regression loss function, named Dense Points} loss to stable the training progress, and a new balanced loss weighting strategy to handle the multi-task losses. With the above novelties, we propose a brand new architecture, named UV R-CNN. Without auxiliary supervision and external knowledge from other tasks, UV R-CNN can handle many complicated issues in dense pose model training progress, achieving 65.0% $AP_{gps}$ and 66.1% $AP_{gpsm}$ on the DensePose-COCO validation subset with ResNet-50-FPN feature extractor, competitive among the state-of-the-art dense human pose estimation methods.

Singular value decomposition (SVD) is one of the most popular compression methods that approximate a target matrix with smaller matrices. However, standard SVD treats the parameters within the matrix with equal importance, which is a simple but unrealistic assumption. The parameters of a trained neural network model may affect task performance unevenly, which suggests non-equal importance among the parameters. Compared to SVD, the decomposition method aware of parameter importance is the more practical choice in real cases. Unlike standard SVD, weighted value decomposition is a non-convex optimization problem that lacks a closed-form solution. We systematically investigated multiple optimization strategies to tackle the problem and examined our method by compressing Transformer-based language models. Further, we designed a metric to predict when the SVD may introduce a significant performance drop, for which our method can be a rescue strategy. The extensive evaluations demonstrate that our method can perform better than current SOTA methods in compressing Transformer-based language models.

我们介绍了第一个基于学习的可重建性预测指标，以改善使用无人机的大规模3D城市场景获取的视图和路径计划。与以前的启发式方法相反，我们的方法学习了一个模型，该模型明确预测了从一组观点重建3D城市场景的能力。为了使这种模型可训练并同时适用于无人机路径计划，我们在培训期间模拟了基于代理的3D场景重建以设置预测。具体而言，我们设计的神经网络经过训练，可以预测场景的重构性，这是代理几何学的函数，一组观点，以及在飞行中获得的一系列场景图像。为了重建一个新的城市场景，我们首先构建了3D场景代理，然后依靠我们网络的预测重建质量和不确定性度量，基于代理几何形状，以指导无人机路径计划。我们证明，与先前的启发式措施相比，我们的数据驱动的可重建性预测与真实的重建质量更加紧密相关。此外，我们学到的预测变量可以轻松地集成到现有的路径计划中，以产生改进。最后，我们根据学习的可重建性设计了一个新的迭代视图计划框架，并在重建合成场景和真实场景时展示新计划者的卓越性能。