变形金刚在NLP和计算机视觉上实现了突破，最近开始在自动驾驶汽车（AV）的轨迹预测中表现出有希望的表现。如何有效地对自我代理与其他道路和动态对象之间的交互关系建模仍然对标准注意模块仍然具有挑战性。在这项工作中，我们提出了一个类似变压器的架构模块MNM网络，该网络配备了新型掩盖的目标调节训练程序，用于AV轨迹预测。最终的模型名为高尔夫球手，取得了最先进的性能，在2022 Waymo Open DataSet Motion Predict挑战中赢得了第二名，并根据Minade排名第一。

Lifelong learning aims to create AI systems that continuously and incrementally learn during a lifetime, similar to biological learning. Attempts so far have met problems, including catastrophic forgetting, interference among tasks, and the inability to exploit previous knowledge. While considerable research has focused on learning multiple input distributions, typically in classification, lifelong reinforcement learning (LRL) must also deal with variations in the state and transition distributions, and in the reward functions. Modulating masks, recently developed for classification, are particularly suitable to deal with such a large spectrum of task variations. In this paper, we adapted modulating masks to work with deep LRL, specifically PPO and IMPALA agents. The comparison with LRL baselines in both discrete and continuous RL tasks shows competitive performance. We further investigated the use of a linear combination of previously learned masks to exploit previous knowledge when learning new tasks: not only is learning faster, the algorithm solves tasks that we could not otherwise solve from scratch due to extremely sparse rewards. The results suggest that RL with modulating masks is a promising approach to lifelong learning, to the composition of knowledge to learn increasingly complex tasks, and to knowledge reuse for efficient and faster learning.

Optimal transport (OT) has become exceedingly popular in machine learning, data science, and computer vision. The core assumption in the OT problem is the equal total amount of mass in source and target measures, which limits its application. Optimal Partial Transport (OPT) is a recently proposed solution to this limitation. Similar to the OT problem, the computation of OPT relies on solving a linear programming problem (often in high dimensions), which can become computationally prohibitive. In this paper, we propose an efficient algorithm for calculating the OPT problem between two non-negative measures in one dimension. Next, following the idea of sliced OT distances, we utilize slicing to define the sliced OPT distance. Finally, we demonstrate the computational and accuracy benefits of the sliced OPT-based method in various numerical experiments. In particular, we show an application of our proposed Sliced-OPT in noisy point cloud registration.

Cardiac resynchronization therapy (CRT) is a treatment that is used to compensate for irregularities in the heartbeat. Studies have shown that this treatment is more effective in heart patients with left bundle branch block (LBBB) arrhythmia. Therefore, identifying this arrhythmia is an important initial step in determining whether or not to use CRT. On the other hand, traditional methods for detecting LBBB on electrocardiograms (ECG) are often associated with errors. Thus, there is a need for an accurate method to diagnose this arrhythmia from ECG data. Machine learning, as a new field of study, has helped to increase human systems' performance. Deep learning, as a newer subfield of machine learning, has more power to analyze data and increase systems accuracy. This study presents a deep learning model for the detection of LBBB arrhythmia from 12-lead ECG data. This model consists of 1D dilated convolutional layers. Attention mechanism has also been used to identify important input data features and classify inputs more accurately. The proposed model is trained and validated on a database containing 10344 12-lead ECG samples using the 10-fold cross-validation method. The final results obtained by the model on the 12-lead ECG data are as follows. Accuracy: 98.80+-0.08%, specificity: 99.33+-0.11 %, F1 score: 73.97+-1.8%, and area under the receiver operating characteristics curve (AUC): 0.875+-0.0192. These results indicate that the proposed model in this study can effectively diagnose LBBB with good efficiency and, if used in medical centers, will greatly help diagnose this arrhythmia and early treatment.

We present a framework for ranking images within their class based on the strength of spurious cues present. By measuring the gap in accuracy on the highest and lowest ranked images (we call this spurious gap), we assess spurious feature reliance for $89$ diverse ImageNet models, finding that even the best models underperform in images with weak spurious presence. However, the effect of spurious cues varies far more dramatically across classes, emphasizing the crucial, often overlooked, class-dependence of the spurious correlation problem. While most spurious features we observe are clarifying (i.e. improving test-time accuracy when present, as is typically expected), we surprisingly find many cases of confusing spurious features, where models perform better when they are absent. We then close the spurious gap by training new classification heads on lowly ranked (i.e. without common spurious cues) images, resulting in improved effective robustness to distribution shifts (ObjectNet, ImageNet-R, ImageNet-Sketch). We also propose a second metric to assess feature reliability, finding that spurious features are generally less reliable than non-spurious (core) ones, though again, spurious features can be more reliable for certain classes. To enable our analysis, we annotated $5,000$ feature-class dependencies over {\it all} of ImageNet as core or spurious using minimal human supervision. Finally, we show the feature discovery and spuriosity ranking framework can be extended to other datasets like CelebA and WaterBirds in a lightweight fashion with only linear layer training, leading to discovering a previously unknown racial bias in the Celeb-A hair classification.

The ability to effectively reuse prior knowledge is a key requirement when building general and flexible Reinforcement Learning (RL) agents. Skill reuse is one of the most common approaches, but current methods have considerable limitations.For example, fine-tuning an existing policy frequently fails, as the policy can degrade rapidly early in training. In a similar vein, distillation of expert behavior can lead to poor results when given sub-optimal experts. We compare several common approaches for skill transfer on multiple domains including changes in task and system dynamics. We identify how existing methods can fail and introduce an alternative approach to mitigate these problems. Our approach learns to sequence existing temporally-extended skills for exploration but learns the final policy directly from the raw experience. This conceptual split enables rapid adaptation and thus efficient data collection but without constraining the final solution.It significantly outperforms many classical methods across a suite of evaluation tasks and we use a broad set of ablations to highlight the importance of differentc omponents of our method.

Federated Learning (FL) is a scheme for collaboratively training Deep Neural Networks (DNNs) with multiple data sources from different clients. Instead of sharing the data, each client trains the model locally, resulting in improved privacy. However, recently so-called targeted poisoning attacks have been proposed that allow individual clients to inject a backdoor into the trained model. Existing defenses against these backdoor attacks either rely on techniques like Differential Privacy to mitigate the backdoor, or analyze the weights of the individual models and apply outlier detection methods that restricts these defenses to certain data distributions. However, adding noise to the models' parameters or excluding benign outliers might also reduce the accuracy of the collaboratively trained model. Additionally, allowing the server to inspect the clients' models creates a privacy risk due to existing knowledge extraction methods. We propose CrowdGuard, a model filtering defense, that mitigates backdoor attacks by leveraging the clients' data to analyze the individual models before the aggregation. To prevent data leaks, the server sends the individual models to secure enclaves, running in client-located Trusted Execution Environments. To effectively distinguish benign and poisoned models, even if the data of different clients are not independently and identically distributed (non-IID), we introduce a novel metric called HLBIM to analyze the outputs of the DNN's hidden layers. We show that the applied significance-based detection algorithm combined can effectively detect poisoned models, even in non-IID scenarios. We show in our extensive evaluation that CrowdGuard can effectively mitigate targeted poisoning attacks and achieve in various scenarios a True-Positive-Rate of 100% and a True-Negative-Rate of 100%.

通过查找图像可能不满意的图像来捕获对象检测器的错误行为，这一兴趣很长。在实际应用（例如自动驾驶）中，对于表征除了简单的检测性能要求之外的潜在失败也至关重要。例如，与远处未遗漏的汽车检测相比，错过对靠近自我车辆的行人的侦查通常需要更仔细的检查。在测试时间预测这种潜在失败的问题在文献和基于检测不确定性的传统方法中被忽略了，因为它们对这种错误的细粒度表征不可知。在这项工作中，我们建议将查找“硬”图像作为基于查询的硬图像检索任务的问题进行重新制定，其中查询是“硬度”的特定定义，并提供了一种简单而直观的方法，可以解决此任务大型查询家庭。我们的方法完全是事后的，不需要地面真相注释，独立于检测器的选择，并且依赖于有效的蒙特卡洛估计，该估计使用简单的随机模型代替地面真相。我们通过实验表明，它可以成功地应用于各种查询中，它可以可靠地识别给定检测器的硬图像，而无需任何标记的数据。我们使用广泛使用的视网膜，更快的RCNN，Mask-RCNN和CASCADE MASK-RCNN对象检测器提供有关排名和分类任务的结果。

现有的一些作品分别研究深神经网络的对抗或自然分布鲁棒性。但是，实际上，模型需要享受两种类型的鲁棒性，以确保可靠性。在这项工作中，我们弥合了这一差距，并表明实际上，对抗性和自然分配鲁棒性之间存在明确的权衡。我们首先考虑具有与核心和虚假功能不相交的高斯数据上的简单线性回归设置。在这种情况下，通过理论和经验分析，我们表明（i）使用$ \ ell_1 $和$ \ ell_2 $规范的对抗性培训增加了对虚假功能的模型依赖； （ii）对于$ \ ell_ \ infty $ versarial训练，仅在伪造功能的比例大于核心功能的范围时才会出现伪造的依赖； （iii）对抗训练可能会在降低分布鲁棒性方面具有意外的后果，特别是当新的测试域中更改虚假相关性时。接下来，我们使用二十个经过对抗训练的模型的测试套件提出了广泛的经验证据受过训练的对应物，验证了我们的理论结果。我们还表明，训练数据中的虚假相关性（保留在测试域中）可以改善对抗性的鲁棒性，表明先前的主张表明对抗性脆弱性植根于虚假相关性是不完整的。

强化学习的许多应用都可以正式化为目标条件的环境，在每个情节中，都有一个“目标”会影响该情节中获得的奖励，但不会影响动态。已经提出了各种技术来提高目标条件环境的性能，例如自动课程生成和目标重新标记。在这项工作中，我们探讨了在目标条件设置中的损失钢筋学习与知识蒸馏之间的联系。特别是：当前的Q值函数和目标Q值估计是该目标的函数，我们想训练Q值函数以匹配其所有目标的目标。因此，我们将基于梯度的注意转移（Zagoruyko和Komodakis 2017）（一种知识蒸馏技术）应用于Q功能更新。我们从经验上表明，当目标空间高维时，这可以提高目标条件的非政策强化学习的性能。我们还表明，在多个同时稀疏目标的情况下，可以对该技术进行调整，以允许有效学习，在这种情况下，代理可以通过在测试时间指定的所有大型目标来实现奖励。最后，为了提供理论支持，我们给出了环境类别的示例，在某些假设下（在某些假设）中，标准的非政策算法至少需要O（d^2）观察到的过渡以学习最佳策略，而我们的建议技术仅需O（ d）过渡，其中d是目标和状态空间的维度。