Developing autonomous vehicles (AVs) helps improve the road safety and traffic efficiency of intelligent transportation systems (ITS). Accurately predicting the trajectories of traffic participants is essential to the decision-making and motion planning of AVs in interactive scenarios. Recently, learning-based trajectory predictors have shown state-of-the-art performance in highway or urban areas. However, most existing learning-based models trained with fixed datasets may perform poorly in continuously changing scenarios. Specifically, they may not perform well in learned scenarios after learning the new one. This phenomenon is called "catastrophic forgetting". Few studies investigate trajectory predictions in continuous scenarios, where catastrophic forgetting may happen. To handle this problem, first, a novel continual learning (CL) approach for vehicle trajectory prediction is proposed in this paper. Then, inspired by brain science, a dynamic memory mechanism is developed by utilizing the measurement of traffic divergence between scenarios, which balances the performance and training efficiency of the proposed CL approach. Finally, datasets collected from different locations are used to design continual training and testing methods in experiments. Experimental results show that the proposed approach achieves consistently high prediction accuracy in continuous scenarios without re-training, which mitigates catastrophic forgetting compared to non-CL approaches. The implementation of the proposed approach is publicly available at https://github.com/BIT-Jack/D-GSM
translated by 谷歌翻译
The goal of multimodal abstractive summarization (MAS) is to produce a concise summary given the multimodal data (text and vision). Existing studies on MAS mainly focus on how to effectively use the extracted visual features, having achieved impressive success on the high-resource English dataset. However, less attention has been paid to the quality of the visual features to the summary, which may limit the model performance especially in the low- and zero-resource scenarios. In this paper, we propose to improve the summary quality through summary-oriented visual features. To this end, we devise two auxiliary tasks including \emph{vision to summary task} and \emph{masked image modeling task}. Together with the main summarization task, we optimize the MAS model via the training objectives of all these tasks. By these means, the MAS model can be enhanced by capturing the summary-oriented visual features, thereby yielding more accurate summaries. Experiments on 44 languages, covering mid-high-, low-, and zero-resource scenarios, verify the effectiveness and superiority of the proposed approach, which achieves state-of-the-art performance under all scenarios.
translated by 谷歌翻译
Given a document in a source language, cross-lingual summarization (CLS) aims at generating a concise summary in a different target language. Unlike monolingual summarization (MS), naturally occurring source-language documents paired with target-language summaries are rare. To collect large-scale CLS samples, existing datasets typically involve translation in their creation. However, the translated text is distinguished from the text originally written in that language, i.e., translationese. Though many efforts have been devoted to CLS, none of them notice the phenomenon of translationese. In this paper, we first confirm that the different approaches to constructing CLS datasets will lead to different degrees of translationese. Then we design systematic experiments to investigate how translationese affects CLS model evaluation and performance when it appears in source documents or target summaries. In detail, we find that (1) the translationese in documents or summaries of test sets might lead to the discrepancy between human judgment and automatic evaluation; (2) the translationese in training sets would harm model performance in the real scene; (3) though machine-translated documents involve translationese, they are very useful for building CLS systems on low-resource languages under specific training strategies. Furthermore, we give suggestions for future CLS research including dataset and model developments. We hope that our work could let researchers notice the phenomenon of translationese in CLS and take it into account in the future.
translated by 谷歌翻译
广告视频编辑旨在将广告视频自动编辑为较短的视频,同时保留广告商传达的连贯内容和关键信息。它主要包含两个阶段:视频细分和段组合。现有方法在视频分割阶段表现良好,但遭受了对额外繁琐模型的依赖性问题,并且在细分组合阶段的性能差。为了解决这些问题,我们提出了M-SAN(多模式段组合网络),该网络可以执行高效且连贯的段组合任务。它利用从段中提取的多模式表示形式,并遵循带有注意机制的编码器ptr-decoder ptr-net框架。重要性补偿奖励是为培训M-SAN设计的。我们在广告客户收集的丰富广告方案下,在ADS-1K数据集上使用1000多个视频进行实验。为了评估这些方法,我们提出了一个统一的imp-coh@Time,该指标可以全面评估同时评估产出的重要性,相干性和持续时间。实验结果表明,我们的方法比随机选择和公制上的先前方法更好的性能。消融实验进一步验证了多模式表示和重要性互动的奖励可显着改善性能。 ADS-1K数据集可用:https://github.com/yunlong10/ads-1k
translated by 谷歌翻译
谷仓(基准自动驾驶机器人导航)挑战在宾夕法尼亚州费城的2022年IEEE国际机器人和自动化国际会议(ICRA 2022)举行。挑战的目的是评估最先进的自动地面导航系统,以安全有效的方式将机器人通过高度约束的环境移动。具体而言,任务是将标准化的差分驱动地面机器人从预定义的开始位置导航到目标位置,而不会与模拟和现实世界中的任何障碍相撞。来自世界各地的五支球队参加了合格的模拟比赛,其中三支受邀在费城会议中心的一组身体障碍课程中相互竞争。竞争结果表明,尽管表面上显得简单,即使对于经验丰富的机器人主义者来说,在高度约束空间中的自主地面导航实际上远非解决问题。在本文中,我们讨论了挑战,前三名获胜团队所使用的方法以及学到的教训以指导未来的研究。
translated by 谷歌翻译
图像文本检索(ITR)在桥接视觉和舌形式方面具有挑战性。对比度学习已被大多数先前的艺术所采用。除了有限的负面图像文本对外,约束学习的能力受到手动加权负对以及对外部知识的不认识的限制。在本文中,我们提出了新型耦合多样性敏感的动量约束学习(编码器),以改善跨模式表示。首先,发明了一种新颖的多样性对比度学习(DCL)体系结构。我们引入了两种模式的动态词典,以扩大图像文本对的比例,并且通过自适应负面对加权实现多样性敏感性。此外,编码器设计了两个分支。一个人从图像/文本中学习实例级的嵌入式,它还基于其嵌入为其输入图像/文本生成伪在线聚类标签。同时,另一个分支学会从常识知识图中查询以形成两种模式的概念级描述符。之后,两个分支都利用DCL来对齐跨模式嵌入空间,而额外的伪聚类标签预测损失则用于促进第二个分支的概念级表示学习。在两个流行的基准测试(即Mscoco和Flicker30k)上进行的广泛实验,验证编码器的表现明显优于最先进的方法。
translated by 谷歌翻译
自动检测异常轨迹是智能运输系统中大量应用的重要问题。许多现有的研究集中在区分异常轨迹和正常轨迹上,忽略了异常轨迹之间的巨大差异。最近的一项研究在鉴定异常轨迹模式方面取得了长足进步,并提出了一种两阶段算法,用于异常轨迹检测和分类(ATDC)。该算法具有出色的性能,但受到了一些局限性,例如高时间的复杂性和不良的解释。在这里,我们对ATDC算法进行了仔细的理论和经验分析,表明可以简化两个阶段的异常得分的计算,并且该算法的第二阶段比第一阶段重要得多。因此,我们开发了一种FastATDC算法,该算法在两个阶段都引入了随机抽样策略。实验结果表明,FastATDC在实际数据集上的速度比ATDC快10到20倍。此外,FastAtDC优于基线算法,与ATDC算法相当。
translated by 谷歌翻译
基于深度学习的面部识别模型容易受到对抗攻击的影响。为了遏制这些攻击,大多数防御方法旨在提高对抗性扰动的识别模型的鲁棒性。但是,这些方法的概括能力非常有限。实际上,它们仍然容易受到看不见的对抗攻击。深度学习模型对于一般的扰动(例如高斯噪音)相当强大。一种直接的方法是使对抗性扰动失活,以便可以轻松地将它们作为一般扰动处理。在本文中,提出了一种称为扰动失活(PIN)的插件对抗防御方法,以使对抗防御的对抗性扰动灭活。我们发现,不同子空间中的扰动对识别模型有不同的影响。应该有一个称为免疫空间的子空间,其中扰动对识别模型的不利影响要比其他子空间更少。因此,我们的方法估计了免疫空间,并通过将它们限制在此子空间中来使对抗性扰动失活。可以将所提出的方法推广到看不见的对抗扰动,因为它不依赖于特定类型的对抗攻击方法。这种方法不仅优于几种最先进的对抗防御方法,而且还通过详尽的实验证明了卓越的概括能力。此外,提出的方法可以成功地应用于四个商业API,而无需额外的培训,这表明可以轻松地将其推广到现有的面部识别系统。源代码可从https://github.com/renmin1991/perturbation in-inactivate获得
translated by 谷歌翻译
在过去的十年中,随着大数据技术的发展,越来越多的患者信息被存储为电子健康记录(EHRS)。利用这些数据,已经提出了各种医生建议系统。通常,此类研究以平坦结构的方式处理EHR数据,每次相遇都被视为一组无序的特征。然而,不得忽略索赔中存储的诸如服务序列之类的异质结构化信息。本文提出了一个医生推荐系统,并嵌入了时间,以使用异质图注意网络重建患者和医生之间的潜在联系。此外,为了解决患者数据共享交叉医院的隐私问题,还提出了一种基于最小化优化模型的联邦分散学习方法。基于图的推荐系统已在EHR数据集上进行了验证。与基线模型相比,提出的方法将AUC提高了6.2%。我们提出的基于联邦的算法不仅产生了虚拟的融合中心的性能,而且还具有O(1/T)的收敛速率。
translated by 谷歌翻译
移动对象(DATMO)的检测和跟踪是自动驾驶环境感知的重要组成部分。虽然使用环绕视图摄像机的3D检测器只是蓬勃发展,但越来越多的趋势是使用不同的基于变压器的方法从透视图的2D特征图中学习3D空间中的查询。本文提出了稀疏的R-CNN 3D(SRCN3D),这是一种新颖的两阶段全横向卷积映射管道,用于环绕视图摄像机检测和跟踪。 SRCN3D采用了级联结构,具有固定数量的提案盒和提案潜在功能的双轨更新。预计提案框可以透视视图,以汇总感兴趣的区域(ROI)本地特征。基于此,提案功能通过动态实例交互式头部进行完善,然后生成分类,并应用于原始边界框。与先前的艺术相比,我们的稀疏功能采样模块仅利用本地2D功能来调整每个相应的3D提案盒,从而导致完整的稀疏范式。提案功能和外观特征均在数据关联过程中采用多刺激性3D多对象跟踪方法。 Nuscenes数据集的广泛实验证明了我们提出的SRCN3D检测器和跟踪器的有效性。代码可在https://github.com/synsin0/srcn3d上找到。
translated by 谷歌翻译