Modern autonomous driving system is characterized as modular tasks in sequential order, i.e., perception, prediction and planning. As sensors and hardware get improved, there is trending popularity to devise a system that can perform a wide diversity of tasks to fulfill higher-level intelligence. Contemporary approaches resort to either deploying standalone models for individual tasks, or designing a multi-task paradigm with separate heads. These might suffer from accumulative error or negative transfer effect. Instead, we argue that a favorable algorithm framework should be devised and optimized in pursuit of the ultimate goal, i.e. planning of the self-driving-car. Oriented at this goal, we revisit the key components within perception and prediction. We analyze each module and prioritize the tasks hierarchically, such that all these tasks contribute to planning (the goal). To this end, we introduce Unified Autonomous Driving (UniAD), the first comprehensive framework up-to-date that incorporates full-stack driving tasks in one network. It is exquisitely devised to leverage advantages of each module, and provide complementary feature abstractions for agent interaction from a global perspective. Tasks are communicated with unified query design to facilitate each other toward planning. We instantiate UniAD on the challenging nuScenes benchmark. With extensive ablations, the effectiveness of using such a philosophy is proven to surpass previous state-of-the-arts by a large margin in all aspects. The full suite of codebase and models would be available to facilitate future research in the community.

训练视觉和语言模型的更多数据总是更好吗？我们研究多模式任务中的知识可传递性。当前的机器学习趋势是假设通过从不同任务加入多个数据集，其整体绩效将有所改善。但是，我们表明，并非所有知识都会很好地转移或对相关任务产生积极影响，即使它们共享一个共同的目标也是如此。我们基于数百种分为4组的视觉和语言任务进行了数百个跨表现的分析。尽管同一组中的任务容易相互改进，但结果表明并非总是如此。其他因素（例如数据集大小或训练阶段）也对知识的转移程度也有很大的影响。

弱监督的时间行动本地化旨在从视频级标签学习实例级别动作模式，其中重大挑战是动作情境混淆。为了克服这一挑战，最近的一个工作建立了一个动作单击监督框。它需要类似的注释成本，但与传统的弱势监督方法相比，可以稳步提高本地化性能。在本文中，通过揭示现有方法的性能瓶颈主要来自后台错误，我们发现更强大的动作定位器可以在背景视频帧上的标签上培训，而不是动作帧上的标签。为此，我们将动作单击监控转换为背景单击监控，并开发一种名为Backtal的新方法。具体地，背塔在背景视频帧上实现两倍建模，即位置建模和特征建模。在适当的建模中，我们不仅在带注释的视频帧上进行监督学习，而且还设计得分分离模块，以扩大潜在的动作帧和背景之间的分数差异。在特征建模中，我们提出了一个亲和力模块，以在计算时间卷积时测量相邻帧之间的特定于帧特定的相似性，并在计算时间卷积时动态地参加信息邻居。进行了三个基准测试的广泛实验，展示了建立的背部的高性能和所提出的背景下单击监督的合理性。代码可用于https://github.com/vididle/backtal。

深度神经网络众所周知，很容易受到对抗性攻击和后门攻击的影响，在该攻击中，对输入的微小修改能够误导模型以给出错误的结果。尽管已经广泛研究了针对对抗性攻击的防御措施，但有关减轻后门攻击的调查仍处于早期阶段。尚不清楚防御这两次攻击之间是否存在任何连接和共同特征。我们对对抗性示例与深神网络的后门示例之间的联系进行了全面的研究，以寻求回答以下问题：我们可以使用对抗检测方法检测后门。我们的见解是基于这样的观察结果，即在推理过程中，对抗性示例和后门示例都有异常，与良性​​样本高度区分。结果，我们修改了四种现有的对抗防御方法来检测后门示例。广泛的评估表明，这些方法可靠地防止后门攻击，其准确性比检测对抗性实例更高。这些解决方案还揭示了模型灵敏度，激活空间和特征空间中对抗性示例，后门示例和正常样本的关系。这能够增强我们对这两次攻击和防御机会的固有特征的理解。

Transforming off-the-shelf deep neural network (DNN) models into dynamic multi-exit architectures can achieve inference and transmission efficiency by fragmenting and distributing a large DNN model in edge computing scenarios (e.g., edge devices and cloud servers). In this paper, we propose a novel backdoor attack specifically on the dynamic multi-exit DNN models. Particularly, we inject a backdoor by poisoning one DNN model's shallow hidden layers targeting not this vanilla DNN model but only its dynamically deployed multi-exit architectures. Our backdoored vanilla model behaves normally on performance and cannot be activated even with the correct trigger. However, the backdoor will be activated when the victims acquire this model and transform it into a dynamic multi-exit architecture at their deployment. We conduct extensive experiments to prove the effectiveness of our attack on three structures (ResNet-56, VGG-16, and MobileNet) with four datasets (CIFAR-10, SVHN, GTSRB, and Tiny-ImageNet) and our backdoor is stealthy to evade multiple state-of-the-art backdoor detection or removal methods.

To better handle long-tail cases in the sequence labeling (SL) task, in this work, we introduce graph neural networks sequence labeling (GNN-SL), which augments the vanilla SL model output with similar tagging examples retrieved from the whole training set. Since not all the retrieved tagging examples benefit the model prediction, we construct a heterogeneous graph, and leverage graph neural networks (GNNs) to transfer information between the retrieved tagging examples and the input word sequence. The augmented node which aggregates information from neighbors is used to do prediction. This strategy enables the model to directly acquire similar tagging examples and improves the general quality of predictions. We conduct a variety of experiments on three typical sequence labeling tasks: Named Entity Recognition (NER), Part of Speech Tagging (POS), and Chinese Word Segmentation (CWS) to show the significant performance of our GNN-SL. Notably, GNN-SL achieves SOTA results of 96.9 (+0.2) on PKU, 98.3 (+0.4) on CITYU, 98.5 (+0.2) on MSR, and 96.9 (+0.2) on AS for the CWS task, and results comparable to SOTA performances on NER datasets, and POS datasets.

Photo-realistic style transfer aims at migrating the artistic style from an exemplar style image to a content image, producing a result image without spatial distortions or unrealistic artifacts. Impressive results have been achieved by recent deep models. However, deep neural network based methods are too expensive to run in real-time. Meanwhile, bilateral grid based methods are much faster but still contain artifacts like overexposure. In this work, we propose the \textbf{Adaptive ColorMLP (AdaCM)}, an effective and efficient framework for universal photo-realistic style transfer. First, we find the complex non-linear color mapping between input and target domain can be efficiently modeled by a small multi-layer perceptron (ColorMLP) model. Then, in \textbf{AdaCM}, we adopt a CNN encoder to adaptively predict all parameters for the ColorMLP conditioned on each input content and style image pair. Experimental results demonstrate that AdaCM can generate vivid and high-quality stylization results. Meanwhile, our AdaCM is ultrafast and can process a 4K resolution image in 6ms on one V100 GPU.

3D人类的姿势和形状估计（又称“人网恢复”）取得了实质性进展。研究人员主要关注新算法的发展，而对涉及的其他关键因素的关注较少。这可能会导致最佳基线，从而阻碍对新设计方法的公平和忠实的评估。为了解决这个问题，这项工作从算法以外的三个探索性观点中提出了首次全面的基准测试研究。 1）数据集。对31个数据集的分析揭示了数据样本的不同影响：具有关键属性的数据集（即多样化的姿势，形状，相机特征，骨干特征）更有效。高质量数据集的战略选择和组合可以显着提高模型性能。 2）骨干。从CNN到变压器的10个骨干的实验表明，从接近任务中学到的知识很容易转移到人网状恢复中。 3）培训策略。正确的增强技术和损失设计至关重要。通过上述发现，我们在具有相对简单的模型的3DPW测试集上实现了47.3 mm的PA-MPJPE。更重要的是，我们为算法的公平比较提供了强大的基准，以及将来建立有效培训配置的建议。代码库可在http://github.com/smplbody/hmr-benchmarks上获得

点击率（CTR）预测的目标是预测用户单击项目的可能性，在推荐系统中变得越来越重要。最近，一些具有自动从他/她的行为中提取用户兴趣的深度学习模型取得了巨大的成功。在这些工作中，注意机制用于选择用户在历史行为中感兴趣的项目，从而提高CTR预测指标的性能。通常，这些细心的模块可以通过使用梯度下降与基本预测变量共同训练。在本文中，我们将用户兴趣建模视为特征选择问题，我们称之为用户兴趣选择。对于这样一个问题，我们在包装法的框架下提出了一种新颖的方法，该方法被称为Meta-wrapper。更具体地说，我们使用可区分的模块作为包装运算符，然后将其学习问题重新提出为连续的二元优化。此外，我们使用元学习算法来求解优化并理论上证明其收敛性。同时，我们还提供了理论分析，以表明我们提出的方法1）效率基于包装器的特征选择，而2）可以更好地抵抗过度拟合。最后，在三个公共数据集上进行的广泛实验表明了我们方法在提高CTR预测的性能方面的优势。

In this paper, we propose a unified whole-body control framework for velocity-controlled mobile collaborative robots which can distribute task motion into the arm and mobile base according to specific task requirements by adjusting weighting factors. Our framework focuses on addressing two challenging issues in whole-body coordination: 1) different dynamic characteristics of the mobile base and the arm; 2) avoidance of violating both safety and configuration constraints. In addition, our controller involves Coupling Dynamic Movement Primitives to enable the essential capabilities for collaboration and interaction applications, such as obstacle avoidance, human teaching, and compliance control. Based on these, we design an adaptive motion mode for intuitive physical human-robot interaction through adjusting the weighting factors. The proposed controller is in closed-form and thus quite computationally efficient. Several typical experiments carried out on a real mobile collaborative robot validate the effectiveness of the proposed controller.