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
对象检测在清洁数据集上取得了有希望的性能,但仍然探讨了如何在对抗性鲁棒性和清洁精度之间实现更好的权衡。对抗性培训是提高稳健性的主流方法,但大多数作品将牺牲清洁精度,以获得比标准训练的坚固性。在本文中,我们提出了统一的解耦特征对准(UDFA),一种新型微调范例,通过完全探索对象检测的自我知识蒸馏和对抗训练之间的组合来实现比现有方法更好的性能。我们首先使用分离的前/后地特征来构建自我知识蒸馏分支,从预磨牙探测器(作为教师)和来自学生探测器的对抗特征表示之间的清洁特征表示之间。然后我们通过将原始分支解耦为自我监督的学习分支和新的自我知识蒸馏分支来探索自我知识蒸馏。通过对Pascal-VOC和MS-Coco基准测试的广泛实验,评估结果表明,UDFA可以超越标准培训和最先进的对抗对象培训方法进行对象检测。例如,与教师探测器相比,我们在GFLV2与RESET-50的方法通过Pascal-Voc上的2.2 AP提高了干净精度;与SOTA对抗性培训方法相比,我们的方法通过1​​.6 AP改善了干净的精度,同时通过0.5 AP改善对抗性鲁棒性。我们的代码将在https://github.com/grispeut/udfa提供。
translated by 谷歌翻译
贝叶斯等级混合集群(BHMC)是一种有趣的模型,可提高传统的贝叶斯分层聚类方法。关于生成过程中的父级节点扩散,BHMC用分层Dirichlet过程混合模型(HDPMM)替换传统的高斯 - 高斯(G2G)内核。然而,BHMC的缺点在于它可以在更高级别(即,靠近根节点的那些)中获得比较高的节点方差。这可以解释为节点之间的分离,特别是较高级别的节点之间的分离可能是弱的。试图克服这一缺点,我们考虑最近的推论框架名为后续正规化,这有助于一种简单的方式对贝叶斯模型施加额外的限制来解决原始模型的一些弱点。因此,为了增强群集的分离,我们将后正则化应用于在层次结构的每个级别的节点上强加对节点上的最大边缘约束。在本文中,我们说明了框架如何与BHMC集成,并通过原始模型实现所需的改进。
translated by 谷歌翻译
Event cameras that asynchronously output low-latency event streams provide great opportunities for state estimation under challenging situations. Despite event-based visual odometry having been extensively studied in recent years, most of them are based on monocular and few research on stereo event vision. In this paper, we present ESVIO, the first event-based stereo visual-inertial odometry, which leverages the complementary advantages of event streams, standard images and inertial measurements. Our proposed pipeline achieves temporal tracking and instantaneous matching between consecutive stereo event streams, thereby obtaining robust state estimation. In addition, the motion compensation method is designed to emphasize the edge of scenes by warping each event to reference moments with IMU and ESVIO back-end. We validate that both ESIO (purely event-based) and ESVIO (event with image-aided) have superior performance compared with other image-based and event-based baseline methods on public and self-collected datasets. Furthermore, we use our pipeline to perform onboard quadrotor flights under low-light environments. A real-world large-scale experiment is also conducted to demonstrate long-term effectiveness. We highlight that this work is a real-time, accurate system that is aimed at robust state estimation under challenging environments.
translated by 谷歌翻译
Egocentric 3D human pose estimation with a single head-mounted fisheye camera has recently attracted attention due to its numerous applications in virtual and augmented reality. Existing methods still struggle in challenging poses where the human body is highly occluded or is closely interacting with the scene. To address this issue, we propose a scene-aware egocentric pose estimation method that guides the prediction of the egocentric pose with scene constraints. To this end, we propose an egocentric depth estimation network to predict the scene depth map from a wide-view egocentric fisheye camera while mitigating the occlusion of the human body with a depth-inpainting network. Next, we propose a scene-aware pose estimation network that projects the 2D image features and estimated depth map of the scene into a voxel space and regresses the 3D pose with a V2V network. The voxel-based feature representation provides the direct geometric connection between 2D image features and scene geometry, and further facilitates the V2V network to constrain the predicted pose based on the estimated scene geometry. To enable the training of the aforementioned networks, we also generated a synthetic dataset, called EgoGTA, and an in-the-wild dataset based on EgoPW, called EgoPW-Scene. The experimental results of our new evaluation sequences show that the predicted 3D egocentric poses are accurate and physically plausible in terms of human-scene interaction, demonstrating that our method outperforms the state-of-the-art methods both quantitatively and qualitatively.
translated by 谷歌翻译
This paper studies audio-visual suppression for egocentric videos -- where the speaker is not captured in the video. Instead, potential noise sources are visible on screen with the camera emulating the off-screen speaker's view of the outside world. This setting is different from prior work in audio-visual speech enhancement that relies on lip and facial visuals. In this paper, we first demonstrate that egocentric visual information is helpful for noise suppression. We compare object recognition and action classification based visual feature extractors, and investigate methods to align audio and visual representations. Then, we examine different fusion strategies for the aligned features, and locations within the noise suppression model to incorporate visual information. Experiments demonstrate that visual features are most helpful when used to generate additive correction masks. Finally, in order to ensure that the visual features are discriminative with respect to different noise types, we introduce a multi-task learning framework that jointly optimizes audio-visual noise suppression and video based acoustic event detection. This proposed multi-task framework outperforms the audio only baseline on all metrics, including a 0.16 PESQ improvement. Extensive ablations reveal the improved performance of the proposed model with multiple active distractors, over all noise types and across different SNRs.
translated by 谷歌翻译
事件摄像机是运动激活的传感器,可捕获像素级照明的变化,而不是具有固定帧速率的强度图像。与标准摄像机相比,它可以在高速运动和高动态范围场景中提供可靠的视觉感知。但是,当相机和场景之间的相对运动受到限制时,例如在静态状态下,事件摄像机仅输出一点信息甚至噪音。尽管标准相机可以在大多数情况下,尤其是在良好的照明条件下提供丰富的感知信息。这两个相机完全是互补的。在本文中,我们提出了一种具有鲁棒性,高智能和实时优化的基于事件的视觉惯性镜(VIO)方法,具有事件角度,基于线的事件功能和基于点的图像功能。提出的方法旨在利用人为场景中的自然场景和基于线路的功能中的基于点的功能,以通过设计良好设计的功能管理提供更多其他结构或约束信息。公共基准数据集中的实验表明,与基于图像或基于事件的VIO相比,我们的方法可以实现卓越的性能。最后,我们使用我们的方法演示了机上闭环自动驾驶四极管飞行和大规模室外实验。评估的视频在我们的项目网站上介绍:https://b23.tv/oe3qm6j
translated by 谷歌翻译
提出了基于可见光通信(VLC)的人类和机器人的合作定位火焰。根据实验系统,我们证明它具有很高的精度和实时性能。
translated by 谷歌翻译
尽管最近在开发动画全身化身方面取得了进展,但服装的现实建模(人类自我表达的核心方面之一)仍然是一个开放的挑战。最先进的物理模拟方法可以以交互速度产生现实行为的服装几何形状。但是,建模光真逼真的外观通常需要基于物理的渲染,这对于交互式应用来说太昂贵了。另一方面,数据驱动的深度外观模型能够有效地产生逼真的外观,但在合成高度动态服装的几何形状和处理具有挑战性的身体套构型方面挣扎。为此,我们通过对服装的明确建模介绍了姿势驱动的化身,这些化身表现出逼真的服装动力学和从现实世界数据中学到的逼真的外观。关键的想法是引入一个在显式几何形状之上运行的神经服装外观模型:在火车时,我们使用高保真跟踪,而在动画时期,我们依靠物理模拟的几何形状。我们的关键贡献是一个具有物理启发的外观网络,能够生成具有视图依赖性和动态阴影效果的影像逼真的外观,即使对于看不见的身体透明构型也是如此。我们对我们的模型进行了彻底的评估,并在几种受试者和不同类型的衣服上展示了不同的动画结果。与以前关于影迷全身化身的工作不同,我们的方法甚至可以为宽松的衣服产生更丰富的动力和更现实的变形。我们还证明,我们的配方自然允许服装与不同人的头像一起使用,同时保持完全动画,因此首次可以采用新颖的衣服来实现逼真的化身。
translated by 谷歌翻译
无标记的单眼3D人类运动捕获(MOCAP)与场景相互作用是一个充满挑战的研究主题,与扩展现实,机器人技术和虚拟头像生成有关。由于单眼环境的固有深度歧义,使用现有方法捕获的3D运动通常包含严重的人工制品,例如不正确的身体场景互穿,抖动和身体漂浮。为了解决这些问题,我们提出了HULC,这是一种新的3D人类MOCAP方法,它知道场景几何形状。 HULC估计3D姿势和密集的身体环境表面接触,以改善3D定位以及受试者的绝对尺度。此外,我们基于新的姿势歧管采样,引入了3D姿势轨迹优化,该采样解决了错误的身体环境互穿。尽管所提出的方法与现有场景感知的单眼MOCAP算法相比需要较少的结构化输入,但它会产生更加可行的姿势:HULC显着且一致地在各种实验和不同指标上都优于现有方法。项目页面:https://vcai.mpi-inf.mpg.de/projects/hulc/。
translated by 谷歌翻译