Robust prediction of citywide traffic flows at different time periods plays a crucial role in intelligent transportation systems. While previous work has made great efforts to model spatio-temporal correlations, existing methods still suffer from two key limitations: i) Most models collectively predict all regions' flows without accounting for spatial heterogeneity, i.e., different regions may have skewed traffic flow distributions. ii) These models fail to capture the temporal heterogeneity induced by time-varying traffic patterns, as they typically model temporal correlations with a shared parameterized space for all time periods. To tackle these challenges, we propose a novel Spatio-Temporal Self-Supervised Learning (ST-SSL) traffic prediction framework which enhances the traffic pattern representations to be reflective of both spatial and temporal heterogeneity, with auxiliary self-supervised learning paradigms. Specifically, our ST-SSL is built over an integrated module with temporal and spatial convolutions for encoding the information across space and time. To achieve the adaptive spatio-temporal self-supervised learning, our ST-SSL first performs the adaptive augmentation over the traffic flow graph data at both attribute- and structure-levels. On top of the augmented traffic graph, two SSL auxiliary tasks are constructed to supplement the main traffic prediction task with spatial and temporal heterogeneity-aware augmentation. Experiments on four benchmark datasets demonstrate that ST-SSL consistently outperforms various state-of-the-art baselines. Since spatio-temporal heterogeneity widely exists in practical datasets, the proposed framework may also cast light on other spatial-temporal applications. Model implementation is available at https://github.com/Echo-Ji/ST-SSL.
translated by 谷歌翻译
We release a new codebase version of the BEVDet, dubbed branch dev2.0. With dev2.0, we propose BEVPoolv2 upgrade the view transformation process from the perspective of engineering optimization, making it free from a huge burden in both calculation and storage aspects. It achieves this by omitting the calculation and preprocessing of the large frustum feature. As a result, it can be processed within 0.82 ms even with a large input resolution of 640x1600, which is 15.1 times the previous fastest implementation. Besides, it is also less cache consumptive when compared with the previous implementation, naturally as it no longer needs to store the large frustum feature. Last but not least, this also makes the deployment to the other backend handy. We offer an example of deployment to the TensorRT backend in branch dev2.0 and show how fast the BEVDet paradigm can be processed on it. Other than BEVPoolv2, we also select and integrate some substantial progress that was proposed in the past year. As an example configuration, BEVDet4D-R50-Depth-CBGS scores 52.3 NDS on the NuScenes validation set and can be processed at a speed of 16.4 FPS with the PyTorch backend. The code has been released to facilitate the study on https://github.com/HuangJunJie2017/BEVDet/tree/dev2.0.
translated by 谷歌翻译
Adding perturbations via utilizing auxiliary gradient information or discarding existing details of the benign images are two common approaches for generating adversarial examples. Though visual imperceptibility is the desired property of adversarial examples, conventional adversarial attacks still generate traceable adversarial perturbations. In this paper, we introduce a novel Adversarial Attack via Invertible Neural Networks (AdvINN) method to produce robust and imperceptible adversarial examples. Specifically, AdvINN fully takes advantage of the information preservation property of Invertible Neural Networks and thereby generates adversarial examples by simultaneously adding class-specific semantic information of the target class and dropping discriminant information of the original class. Extensive experiments on CIFAR-10, CIFAR-100, and ImageNet-1K demonstrate that the proposed AdvINN method can produce less imperceptible adversarial images than the state-of-the-art methods and AdvINN yields more robust adversarial examples with high confidence compared to other adversarial attacks.
translated by 谷歌翻译
本文重新讨论了一个非常简单但非常有效的计算范式,深度共同学习(DML)。我们观察到,有效性与其出色的概括质量高度相关。在本文中,我们从新的角度来解释了DML的性能改善,即这大约是贝叶斯后的采样程序。这也为应用R \'{e} nyi Divergence改善原始DML的基础建立了基础,因为它带来了先验的差异控制(在DML的上下文中)。因此,我们提出了r \'{e} nyi Divergence深度共同学习(RDML)。我们的经验结果代表了DML和\ renyi {}差异的婚姻的优势。R \'{E} nyi Divergence施加的灵活控制能够进一步改进DML,以学习更好的广义模型。
translated by 谷歌翻译
如今,基础模型已成为人工智能中的基本基础设施之一,铺平了通往通用情报的方式。但是,现实提出了两个紧急挑战:现有的基础模型由英语社区主导;用户通常会获得有限的资源,因此不能总是使用基础模型。为了支持中文社区的发展,我们介绍了一个名为Fengshenbang的开源项目,该项目由认知计算与自然语言研究中心(CCNL)领导。我们的项目具有全面的功能,包括大型预培训模型,用户友好的API,基准,数据集等。我们将所有这些都包装在三个子项目中:风水次模型,风水框架和狂热基准。 Fengshenbang的开源路线图旨在重新评估中国预培训的大型大型模型的开源社区,促使整个中国大型模型社区的发展。我们还希望构建一个以用户为中心的开源生态系统,以允许个人访问所需的模型以匹配其计算资源。此外,我们邀请公司,大学和研究机构与我们合作建立大型开源模型的生态系统。我们希望这个项目将成为中国认知情报的基础。
translated by 谷歌翻译
尽管在情感分析方面取得了巨大的成功,但现有的神经模型在隐式情感分析中挣扎。这可能是由于它们可能会锁定虚假的相关性(例如,“捷径”,例如,仅关注明确的情感词),从而破坏了学习模型的有效性和鲁棒性。在这项工作中,我们提出了一种使用仪器变量(ISAIV)的因果干预模型,用于隐式情感分析。我们首先从因果角度审查情感分析,并分析此任务中存在的混杂因素。然后,我们引入了一个仪器变量,以消除混杂的因果效应,从而在句子和情感之间提取纯粹的因果效应。我们将所提出的ISAIV模型与几个强大的基线进行比较,同时是一般的隐式情感分析和基于方面的隐式情感分析任务。结果表明我们模型的巨大优势以及隐性情感推理的功效。
translated by 谷歌翻译
为了应对人类检测对标签数据和隐私问题的不断增长的需求,合成数据已被用作替代品,并在人类检测和跟踪任务中显示出令人鼓舞的结果。我们参加了第七届基准测试多目标跟踪(BMTT)的研讨会,主题是“合成数据可以带我们多远”?我们的解决方案Pietrack是根据合成数据开发的,而无需使用任何预训练的权重。我们提出了一种自我监督的域适应方法,该方法能够减轻合成(例如Motsynth)和真实数据(例如Mot17)之间的域移位问题,而无需涉及额外的人类标签。通过利用拟议的多尺度合奏推理,我们在MOT17测试集中获得了58.7的最终HOTA得分,在挑战中排名第三。
translated by 谷歌翻译
单帧数据包含有限信息,该信息限制了现有的基于视觉的多相机3D对象检测范例的性能。为了从根本上推动该区域的性能边界,提出了一种新颖的范式BEVDET4D,以将可扩展的BEVDET范式从仅空间的3D空间提升到空间 - 时空4D空间。我们使用一些修改来升级幼稚的BEVDET框架,仅将上一个帧中的功能与当前帧中的相应框架融合在一起。通过这种方式,借助额外的计算预算,我们可以通过查询和比较两个候选功能来访问临时提示。除此之外,我们通过消除学习目标中的自我运动和时间的因素来简化速度预测的任务。结果,具有鲁棒泛化性能的BEVDET4D将速度误差降低到-62.9%。这使得基于视觉的方法首次与在这方面依赖激光雷达或雷达的方法相提并论。在挑战基准Nuscenes上,我们报告了54.5%NDS的新记录,其高性能配置称为BEVDET4D-BASE,它超过了先前领先的方法BEVDET基本底座,而BEVDET基本却 + +7.3%NDS。源代码可在https://github.com/huangjunjie2017/bevdet上公开研究。
translated by 谷歌翻译
网络在许多现实世界应用程序中无处不在(例如,编码信任/不信任关系的社交网络,由时间序列数据引起的相关网络)。尽管许多网络都是签名或指示的,或者两者都在图形神经网络(GNN)上缺少统一的软件包,专门为签名和定向网络设计。在本文中,我们提出了Pytorch几何签名的指示,这是一个填补此空白的软件包。在此过程中,我们还提供了简短的审查调查,以分析签名和定向网络的分析,讨论相关实验中使用的数据,提供提出的方法概述,并通过实验评估实施方法。深度学习框架包括易于使用的GNN模型,合成和现实世界数据,以及针对签名和定向网络的特定任务评估指标和损失功能。作为Pytorch几何形状的扩展库,我们提出的软件由开源版本,详细文档,连续集成,单位测试和代码覆盖范围检查维护。我们的代码可在\ url {https://github.com/sherylhyx/pytorch_geometric_signed_directed}上公开获得。
translated by 谷歌翻译
自然语言理解(NLU)模型倾向于依靠虚假的相关性(即数据集偏见)来在分布数据集上实现高性能,但在分布外部的数据集中的性能差。大多数现有的偏见方法通常都以偏见的特征(即引起这种虚假相关性的表面特征)来识别和削弱这些样品。但是,下降加权这些样品阻碍了从这些样品的无偏见部分学习的模型。为了应对这一挑战,在本文中,我们建议从特征空间的角度以细粒度的方式消除虚假的相关性。具体而言,我们引入了随机傅立叶特征和加权重采样,以将功能之间的依赖关系解释以减轻虚假相关性。在获得非相关的功能后,我们进一步设计了一种基于相互信息的方法来净化它们,这迫使模型学习与任务更相关的功能。对两个经过良好研究的NLU任务进行的广泛实验表明,我们的方法优于其他比较方法。
translated by 谷歌翻译