循环闭合是同时定位和映射(SLAM)系统的重要组成部分。大型视野(FOV)摄像机在SLAM领域受到了广泛的关注,因为它们可以利用全景图像上更多的周围功能。在大型VIO中,用于结合位于全景镜头负面平面上的信息提示,图像特征由具有单位长度的三维矢量表示。虽然全景FOV似乎对于循环封闭是有利的,但在大角度的差异下,这些好处不能轻易实现,在大型角度差异下,循环封闭帧几乎无法通过现有方法匹配。在这项工作中,为了完全释放超宽FOV的潜力,我们建议利用VIO系统的态度信息来指导环路闭合的特征点检测。随着宽圈全景数据上的循环封闭进一步带有许多离群值,因此传统的异常拒绝方法并非直接适用。为了解决此问题,我们提出了一个基于单位长度表示的新离群拒绝方法的循环封闭框架,以提高LF-VIO的准确性。在公共Palvio数据集上,进行了一组全面的实验,并提出的LF-Vio-loop优于最先进的视觉惯性化学方法。我们的代码将在https://github.com/flysoaryun/lf-vio-loop上开放。
translated by 谷歌翻译
尽管深入的强化学习(DRL)在包括机器人技术在内的许多学科中都很流行,但最先进的DRL算法仍然难以学习长途,多步骤和稀疏奖励任务,例如仅在只有一项任务的情况下堆叠几个块 - 集合奖励信号。为了提高此类任务的学习效率,本文提出了一种称为A^2的DRL探索技术,该技术集成了受人类经验启发的两个组成部分:抽象演示和适应性探索。 A^2首先将复杂的任务分解为子任务,然后提供正确的子任务订单以学习。在训练过程中,该代理商会自适应地探索环境,对良好的子任务的行为更确定性,并且更随机地对不良的子任务子任务。消融和比较实验是对几个网格世界任务和三个机器人操纵任务进行的。我们证明A^2可以帮助流行的DRL算法(DQN,DDPG和SAC)在这些环境中更有效,稳定地学习。
translated by 谷歌翻译
近年来,Experts(MOE)的混合物已成为一种有前途的深度学习技术,可以将模型能力扩展为万亿多个参数,同时通过稀疏计算降低计算成本。虽然MoE开设了一个非常大的模型的新领域,但由于MOE的动态性质与系统的静态平行性/管道层之间的不匹配,因此其数以千计的GPU的实现受到限制。我们提出了Tutel,这是一种具有动态自适应并行性和管道的高度可扩展的堆栈设计和实现。 TUTEL在运行时提供自适应并行性切换和自适应管道,分别达到1.74倍和2.00倍的单MOE层加速度。我们还提出了一种用于MOE通信速度的新颖的二维层次结构算法,该算法的表现超过了2,048 GPU的先前最先前的最新时间。 Tutel汇总了所有技术,最终在16 GPU和2,048 GPU上分别提供了4.96倍和5.75倍的加速度,分别通过Fairseq:Meta的Facebook AI AI研究序列到序列工具Kit(Tutel(Tutel)(Tutel)(Tutel)(现在由Fairseq部分采用)。 Tutel源代码可在公共场所获得:https://github.com/microsoft/tutel。我们的评估表明,Tutel有效,有效地运行了一个基于现实的MOE模型,名为Swinv2-Moe,建立在Swin Transformer V2上,这是一种最先进的计算机视觉体系结构。在效率方面,Tutel加速了Swinv2-MoE,在FairSeq的训练和推理中分别达到1.55倍和2.11倍的速度。关于有效性,SWINV2-MOE模型在预训练和下游计算机视觉任务(例如可可对象检测)方面都比对应的密度密度模型都达到了卓越的精度,这表明Tutel准备对端到端现实世界模型训练的准备就绪和推理。 Swinv2-Moe在https://github.com/microsoft/swin-transformer中开放。
translated by 谷歌翻译
Few-shot object detection (FSOD), which aims at learning a generic detector that can adapt to unseen tasks with scarce training samples, has witnessed consistent improvement recently. However, most existing methods ignore the efficiency issues, e.g., high computational complexity and slow adaptation speed. Notably, efficiency has become an increasingly important evaluation metric for few-shot techniques due to an emerging trend toward embedded AI. To this end, we present an efficient pretrain-transfer framework (PTF) baseline with no computational increment, which achieves comparable results with previous state-of-the-art (SOTA) methods. Upon this baseline, we devise an initializer named knowledge inheritance (KI) to reliably initialize the novel weights for the box classifier, which effectively facilitates the knowledge transfer process and boosts the adaptation speed. Within the KI initializer, we propose an adaptive length re-scaling (ALR) strategy to alleviate the vector length inconsistency between the predicted novel weights and the pretrained base weights. Finally, our approach not only achieves the SOTA results across three public benchmarks, i.e., PASCAL VOC, COCO and LVIS, but also exhibits high efficiency with 1.8-100x faster adaptation speed against the other methods on COCO/LVIS benchmark during few-shot transfer. To our best knowledge, this is the first work to consider the efficiency problem in FSOD. We hope to motivate a trend toward powerful yet efficient few-shot technique development. The codes are publicly available at https://github.com/Ze-Yang/Efficient-FSOD.
translated by 谷歌翻译
光流估计是自动驾驶和机器人系统系统中的一项基本任务,它可以在时间上解释流量场景。自动驾驶汽车显然受益于360 {\ deg}全景传感器提供的超宽视野(FOV)。但是,由于全景相机的独特成像过程,专为针孔图像设计的模型不会令人满意地概括为360 {\ deg}全景图像。在本文中,我们提出了一个新颖的网络框架 - panoflow,以学习全景图像的光流。为了克服全景转化中等应角投影引起的扭曲,我们设计了一种流动失真增强(FDA)方法,其中包含径向流量失真(FDA-R)或等骨流量失真(FDA-E)。我们进一步研究了全景视频的环状光流的定义和特性,并通过利用球形图像的环状来推断360 {\ deg}光流并将大型位移转换为相对小的位移,从而提出了环状流量估计(CFE)方法移位。 Panoflow适用于任何现有的流量估计方法,并从狭窄的FOL流量估计的进度中受益。此外,我们创建并释放基于CARLA的合成全景数据集Flow360,以促进训练和定量分析。 Panoflow在公共Omniflownet和已建立的Flow360基准中实现了最先进的表现。我们提出的方法将Flow360上的端点误差(EPE)降低了27.3%。在Omniflownet上,Panoflow获得了3.17像素的EPE,从最佳发布的结果中降低了55.5%的误差。我们还通过收集工具和公共现实世界中的全球数据集对我们的方法进行定性验证我们的方法,这表明对现实世界导航应用程序的强大潜力和稳健性。代码和数据集可在https://github.com/masterhow/panoflow上公开获取。
translated by 谷歌翻译
视觉惯性化学测定法吸引了自主驾驶和机器人技术领域的广泛关注。视场(FOV)的大小在视觉播音(VO)和视觉惯性二次测量法(VO)中起着重要作用,作为大型FOV,可以感知各种周围的场景元素和特征。但是,当摄像机的字段到达负半平面时,就不能简单地使用[u,v,1]^t来表示图像特征点。为了解决这个问题,我们建议LF-VIO,这是一个具有极大FOV的相机的实时VIO框架。我们利用具有单位长度的三维矢量来表示特征点,并设计一系列算法来克服这一挑战。为了解决带有地位的位置和姿势的全景视觉探针数据集的稀缺性,我们介绍了Palvio数据集,该数据集用具有360 {\ deg} x的整个FOV的全景环形镜头(PAL)系统收集(40 {\ deg}) -120 {\ deg})和IMU传感器。有了全面的实验,在已建立的Palvio基准和公共Fisheye摄像机数据集上验证了建议的LF-VIO,其FOV为360 {\ deg} x(0 {\ deg} -93.5 {\ deg})。 LF-VIO优于最先进的视觉惯性 - 调节法。我们的数据集和代码可在https://github.com/flysoaryun/lf-vio上公开提供。
translated by 谷歌翻译
本文介绍了使用变压器解决关键点检测和实例关联的新方法。对于自下而上的多人姿势估计模型,他们需要检测关键点并在关键点之间学习关联信息。我们认为这些问题可以完全由变压器解决。具体而言,变压器中的自我关注测量任何一对位置之间的依赖性,这可以为关键点分组提供关联信息。但是,天真的注意力模式仍然没有主观控制,因此无法保证关键点始终会参加它们所属的实例。为了解决它,我们提出了一种监督多人关键点检测和实例关联的自我关注的新方法。通过使用实例掩码来监督自我关注的实例感知,我们可以基于成对引人注定分数为其对应的实例分配检测到的关键字,而无需使用预定义的偏移量字段或嵌入像基于CNN的自下而上模型。我们方法的另一个好处是可以从监督的注意矩阵直接获得任何数量的人的实例分段结果,从而简化了像素分配管道。对Coco多人关键点检测挑战和人实例分割任务的实验证明了所提出的方法的有效性和简单性,并显示出于针对特定目的控制自我关注行为的有希望的方法。
translated by 谷歌翻译
Modern object detectors rely heavily on rectangular bounding boxes, such as anchors, proposals and the final predictions, to represent objects at various recognition stages. The bounding box is convenient to use but provides only a coarse localization of objects and leads to a correspondingly coarse extraction of object features. In this paper, we present RepPoints (representative points), a new finer representation of objects as a set of sample points useful for both localization and recognition. Given ground truth localization and recognition targets for training, RepPoints learn to automatically arrange themselves in a manner that bounds the spatial extent of an object and indicates semantically significant local areas. They furthermore do not require the use of anchors to sample a space of bounding boxes. We show that an anchor-free object detector based on RepPoints can be as effective as the state-of-the-art anchor-based detection methods, with 46.5 AP and 67.4 AP 50 on the COCO test-dev detection benchmark, using ResNet-101 model. Code is available at https://github.com/microsoft/RepPoints.
translated by 谷歌翻译
We revisit a simple Learning-from-Scratch baseline for visuo-motor control that uses data augmentation and a shallow ConvNet. We find that this baseline has competitive performance with recent methods that leverage frozen visual representations trained on large-scale vision datasets.
translated by 谷歌翻译
Visual Place Recognition is an essential component of systems for camera localization and loop closure detection, and it has attracted widespread interest in multiple domains such as computer vision, robotics and AR/VR. In this work, we propose a faster, lighter and stronger approach that can generate models with fewer parameters and can spend less time in the inference stage. We designed RepVGG-lite as the backbone network in our architecture, it is more discriminative than other general networks in the Place Recognition task. RepVGG-lite has more speed advantages while achieving higher performance. We extract only one scale patch-level descriptors from global descriptors in the feature extraction stage. Then we design a trainable feature matcher to exploit both spatial relationships of the features and their visual appearance, which is based on the attention mechanism. Comprehensive experiments on challenging benchmark datasets demonstrate the proposed method outperforming recent other state-of-the-art learned approaches, and achieving even higher inference speed. Our system has 14 times less params than Patch-NetVLAD, 6.8 times lower theoretical FLOPs, and run faster 21 and 33 times in feature extraction and feature matching. Moreover, the performance of our approach is 0.5\% better than Patch-NetVLAD in Recall@1. We used subsets of Mapillary Street Level Sequences dataset to conduct experiments for all other challenging conditions.
translated by 谷歌翻译