Despite some successful applications of goal-driven navigation, existing deep reinforcement learning-based approaches notoriously suffers from poor data efficiency issue. One of the reasons is that the goal information is decoupled from the perception module and directly introduced as a condition of decision-making, resulting in the goal-irrelevant features of the scene representation playing an adversary role during the learning process. In light of this, we present a novel Goal-guided Transformer-enabled reinforcement learning (GTRL) approach by considering the physical goal states as an input of the scene encoder for guiding the scene representation to couple with the goal information and realizing efficient autonomous navigation. More specifically, we propose a novel variant of the Vision Transformer as the backbone of the perception system, namely Goal-guided Transformer (GoT), and pre-train it with expert priors to boost the data efficiency. Subsequently, a reinforcement learning algorithm is instantiated for the decision-making system, taking the goal-oriented scene representation from the GoT as the input and generating decision commands. As a result, our approach motivates the scene representation to concentrate mainly on goal-relevant features, which substantially enhances the data efficiency of the DRL learning process, leading to superior navigation performance. Both simulation and real-world experimental results manifest the superiority of our approach in terms of data efficiency, performance, robustness, and sim-to-real generalization, compared with other state-of-art baselines. Demonstration videos are available at \colorb{https://youtu.be/93LGlGvaN0c.

早期退出是提高深网推理效率的有效范例。通过构建具有不同资源需求的分类器（出口），此类网络可以在早期出口处输出简单的样本，从而消除了执行更深层的需求。尽管现有作品主要关注多EXIT网络的建筑设计，但此类模型的培训策略在很大程度上没有探索。当前的最新模型在培训期间对所有样品进行了相同的处理。但是，在测试过程中的早期外观行为被忽略了，从而导致训练和测试之间存在差距。在本文中，我们建议通过样品加权来弥合这一差距。从直觉上讲，简单的样品通常在推理期间在网络早期退出，应该为培训早期分类器提供更多贡献。但是，晚期分类器应强调硬样品的培训（主要是从更深层退出）。我们的工作建议采用一个体重预测网络，以加重每个出口处不同训练样本的损失。这个重量预测网络和骨干模型在具有新的优化目标的元学习框架下共同优化。通过将推断期间的适应性行为带入训练阶段，我们表明拟议的加权机制始终提高分类准确性和推理效率之间的权衡。代码可在https://github.com/leaplabthu/l2w-den上找到。

决策对于自动驾驶的车道变化至关重要。强化学习（RL）算法旨在确定各种情况下的行为价值，因此它们成为解决决策问题的有前途的途径。但是，运行时安全性较差，阻碍了基于RL的决策策略，从实践中进行了复杂的驾驶任务。为了解决这个问题，本文将人类的示范纳入了基于RL的决策策略中。人类受试者在驾驶模拟器中做出的决定被视为安全的示范，将其存储到重播缓冲液中，然后用来增强RL的训练过程。建立了一个复杂的车道变更任务，以检查开发策略的性能。仿真结果表明，人类的演示可以有效地提高RL决策的安全性。而拟议的策略超过了其他基于学习的决策策略，就多种驾驶表演而言。

Deep Q-Network（DQN）算法解决的大规模实践工作表明，随机政策尽管简单，但最常用的探索方法是最常用的探索方法。但是，大多数现有的随机探索方法要么探索新的动作，无论Q值如何，要么不可避免地将偏见引入学习过程中，以将抽样与Q值搭配。在本文中，我们提出了一种新颖的偏好指导$ \ epsilon $ greedy Exploration算法，该算法可以在不引入其他偏见的情况下根据Q值的Q值有效地学习动作分布。具体而言，我们设计了一个由两个分支组成的双重体系结构，其中一个是DQN的副本，即Q Branch。我们称为首选项分支的另一个分支，了解了DQN隐式所遵循的动作偏好。从理论上讲，我们证明了策略改进定理适用于首选项指导的$ \ epsilon $ greedy策略，并在实验上表明，推断的动作偏好分布与相应的Q值的景观保持一致。因此，偏好引导的$ \ epsilon $ - 秘密探索激励DQN代理采取多种操作，即可以更频繁地采样较大的Q值的行动，而使用较小的Q值的行动仍然可以探索，因此仍有机会。鼓励探索。我们在九个不同的环境中使用四个众所周知的DQN变体评估了提出的方法。广泛的结果证实了我们提出的方法在性能和收敛速度方面的优势。索引术语 - 偏好引导的探索，随机政策，数据效率，深度强化学习，深度Q学习。

基础模型由于在广泛的下游应用中的有效性而受到了很多关注。尽管在体系结构方面存在很大的融合，但大多数审慎的模型通常仍用于特定任务或模式。在这项工作中，我们建议将语言模型用作各种基础模型的通用接口。一系列预处理的编码者感知到了多种方式（例如视觉和语言），并与扮演通用任务层角色的语言模型对接。我们提出了一个半伴侣的语言建模目标，以共同确定界面和模块化编码器。我们从因果关系和非因果建模中涵盖了优势和能力，从而结合了两个世界的最佳状态。具体而言，所提出的方法不仅从因果语言建模中继承了内在学习和开放式生成的能力，而且由于双向编码器而有利于填补。更重要的是，我们的方法无缝地解锁了上述功能的组合，例如，通过填充编码器启用了文本学习或指导。各种仅语言和视觉语言基准的实验结果表明，我们的模型表现优于或与鉴定，零弹性概括和几乎没有的学习的专业模型竞争。

空间冗余广泛存在于视觉识别任务中，即图像或视频帧中的判别特征通常对应于像素的子集，而剩余区域与手头的任务无关。因此，在时间和空间消耗方面，处理具有相等计算量的所有像素的静态模型导致相当冗余。在本文中，我们将图像识别问题标准为顺序粗致细特征学习过程，模仿人类视觉系统。具体地，所提出的浏览和焦点网络（GFNET）首先以低分辨率比例提取输入图像的快速全局表示，然后策略性地参加一系列突出（小）区域以学习更精细的功能。顺序过程自然地促进了在测试时间的自适应推断，因为一旦模型对其预测充分信心，可以终止它，避免了进一步的冗余计算。值得注意的是，在我们模型中定位判别区域的问题被制定为增强学习任务，因此不需要除分类标签之外的其他手动注释。 GFNET是一般的，灵活，因为它与任何现成的骨干网型号（例如MobileCenets，Abservennet和TSM）兼容，可以方便地部署为特征提取器。对各种图像分类和视频识别任务的广泛实验以及各种骨干模型，证明了我们方法的显着效率。例如，它通过1.3倍降低了高效MobileNet-V3的平均等待时间，而不会牺牲精度。代码和预先训练的模型可在https://github.com/blackfeather-wang/gfnet-pytorch获得。

Reinforcement learning (RL) requires skillful definition and remarkable computational efforts to solve optimization and control problems, which could impair its prospect. Introducing human guidance into reinforcement learning is a promising way to improve learning performance. In this paper, a comprehensive human guidance-based reinforcement learning framework is established. A novel prioritized experience replay mechanism that adapts to human guidance in the reinforcement learning process is proposed to boost the efficiency and performance of the reinforcement learning algorithm. To relieve the heavy workload on human participants, a behavior model is established based on an incremental online learning method to mimic human actions. We design two challenging autonomous driving tasks for evaluating the proposed algorithm. Experiments are conducted to access the training and testing performance and learning mechanism of the proposed algorithm. Comparative results against the state-of-the-art methods suggest the advantages of our algorithm in terms of learning efficiency, performance, and robustness.

Despite the remarkable success achieved by graph convolutional networks for functional brain activity analysis, the heterogeneity of functional patterns and the scarcity of imaging data still pose challenges in many tasks. Transferring knowledge from a source domain with abundant training data to a target domain is effective for improving representation learning on scarce training data. However, traditional transfer learning methods often fail to generalize the pre-trained knowledge to the target task due to domain discrepancy. Self-supervised learning on graphs can increase the generalizability of graph features since self-supervision concentrates on inherent graph properties that are not limited to a particular supervised task. We propose a novel knowledge transfer strategy by integrating meta-learning with self-supervised learning to deal with the heterogeneity and scarcity of fMRI data. Specifically, we perform a self-supervised task on the source domain and apply meta-learning, which strongly improves the generalizability of the model using the bi-level optimization, to transfer the self-supervised knowledge to the target domain. Through experiments on a neurological disorder classification task, we demonstrate that the proposed strategy significantly improves target task performance by increasing the generalizability and transferability of graph-based knowledge.

Airport runway segmentation can effectively reduce the accident rate during the landing phase, which has the largest risk of flight accidents. With the rapid development of deep learning, related methods have good performance on segmentation tasks and can be well adapted to complex scenes. However, the lack of large-scale, publicly available datasets in this field makes the development of methods based on deep learning difficult. Therefore, we propose a Benchmark for Airport Runway Segmentation, named BARS. Meanwhile, a semi-automatic annotation pipeline is designed to reduce the workload of annotation. BARS has the largest dataset with the richest categories and the only instance annotation in the field. The dataset, which is collected using the X-Plane simulation platform, contains 10,002 images and 29,347 instances with three categories. We evaluate eight representative instance segmentation methods on BARS and analyze their performance. Based on the characteristic of the airport runway with a regular shape, we propose a plug-and-play smoothing post-processing module (SPPM) and a contour point constraint loss (CPCL) function to smooth segmentation results for mask-based and contour-based methods, respectively. Furthermore, a novel evaluation metric named average smoothness (AS) is developed to measure smoothness. The experiments show that existing instance segmentation methods can achieve prediction results with good performance on BARS. SPPM and CPCL can improve the average accuracy by 0.9% and 1.13%, respectively. And the average smoothness enhancements for SPPM and CPCL are more than 50% and 28%, respectively.

This paper studies 3D dense shape correspondence, a key shape analysis application in computer vision and graphics. We introduce a novel hybrid geometric deep learning-based model that learns geometrically meaningful and discretization-independent features with a U-Net model as the primary node feature extraction module, followed by a successive spectral-based graph convolutional network. To create a diverse set of filters, we use anisotropic wavelet basis filters, being sensitive to both different directions and band-passes. This filter set overcomes the over-smoothing behavior of conventional graph neural networks. To further improve the model's performance, we add a function that perturbs the feature maps in the last layer ahead of fully connected layers, forcing the network to learn more discriminative features overall. The resulting correspondence maps show state-of-the-art performance on the benchmark datasets based on average geodesic errors and superior robustness to discretization in 3D meshes. Our approach provides new insights and practical solutions to the dense shape correspondence research.