Fine-grained capturing of 3D HOI boosts human activity understanding and facilitates downstream visual tasks, including action recognition, holistic scene reconstruction, and human motion synthesis. Despite its significance, existing works mostly assume that humans interact with rigid objects using only a few body parts, limiting their scope. In this paper, we address the challenging problem of f-AHOI, wherein the whole human bodies interact with articulated objects, whose parts are connected by movable joints. We present CHAIRS, a large-scale motion-captured f-AHOI dataset, consisting of 16.2 hours of versatile interactions between 46 participants and 81 articulated and rigid sittable objects. CHAIRS provides 3D meshes of both humans and articulated objects during the entire interactive process, as well as realistic and physically plausible full-body interactions. We show the value of CHAIRS with object pose estimation. By learning the geometrical relationships in HOI, we devise the very first model that leverage human pose estimation to tackle the estimation of articulated object poses and shapes during whole-body interactions. Given an image and an estimated human pose, our model first reconstructs the pose and shape of the object, then optimizes the reconstruction according to a learned interaction prior. Under both evaluation settings (e.g., with or without the knowledge of objects' geometries/structures), our model significantly outperforms baselines. We hope CHAIRS will promote the community towards finer-grained interaction understanding. We will make the data/code publicly available.
translated by 谷歌翻译
State-of-the-art 3D semantic segmentation models are trained on the off-the-shelf public benchmarks, but they often face the major challenge when these well-trained models are deployed to a new domain. In this paper, we propose an Active-and-Adaptive Segmentation (ADAS) baseline to enhance the weak cross-domain generalization ability of a well-trained 3D segmentation model, and bridge the point distribution gap between domains. Specifically, before the cross-domain adaptation stage begins, ADAS performs an active sampling operation to select a maximally-informative subset from both source and target domains for effective adaptation, reducing the adaptation difficulty under 3D scenarios. Benefiting from the rise of multi-modal 2D-3D datasets, ADAS utilizes a cross-modal attention-based feature fusion module that can extract a representative pair of image features and point features to achieve a bi-directional image-point feature interaction for better safe adaptation. Experimentally, ADAS is verified to be effective in many cross-domain settings including: 1) Unsupervised Domain Adaptation (UDA), which means that all samples from target domain are unlabeled; 2) Unsupervised Few-shot Domain Adaptation (UFDA) which means that only a few unlabeled samples are available in the unlabeled target domain; 3) Active Domain Adaptation (ADA) which means that the selected target samples by ADAS are manually annotated. Their results demonstrate that ADAS achieves a significant accuracy gain by easily coupling ADAS with self-training methods or off-the-shelf UDA works.
translated by 谷歌翻译
Since the recent success of Vision Transformers (ViTs), explorations toward transformer-style architectures have triggered the resurgence of modern ConvNets. In this work, we explore the representation ability of DNNs through the lens of interaction complexities. We empirically show that interaction complexity is an overlooked but essential indicator for visual recognition. Accordingly, a new family of efficient ConvNets, named MogaNet, is presented to pursue informative context mining in pure ConvNet-based models, with preferable complexity-performance trade-offs. In MogaNet, interactions across multiple complexities are facilitated and contextualized by leveraging two specially designed aggregation blocks in both spatial and channel interaction spaces. Extensive studies are conducted on ImageNet classification, COCO object detection, and ADE20K semantic segmentation tasks. The results demonstrate that our MogaNet establishes new state-of-the-art over other popular methods in mainstream scenarios and all model scales. Typically, the lightweight MogaNet-T achieves 80.0\% top-1 accuracy with only 1.44G FLOPs using a refined training setup on ImageNet-1K, surpassing ParC-Net-S by 1.4\% accuracy but saving 59\% (2.04G) FLOPs.
translated by 谷歌翻译
磁共振光谱成像(MRSI)是量化体内代谢物的必不可少的工具,但是低空间分辨率限制了其临床应用。基于深度学习的超分辨率方法为改善MRSI的空间分辨率提供了有希望的结果,但是与实验获得的高分辨率图像相比,超级分辨图像通常是模糊的。已经使用生成对抗网络进行了尝试,以提高图像视觉质量。在这项工作中,我们考虑了另一种类型的生成模型,即基于流的模型,与对抗网络相比,训练更稳定和可解释。具体而言,我们提出了一个基于流动的增强器网络,以提高超分辨率MRSI的视觉质量。与以前的基于流的模型不同,我们的增强器网络包含了来自其他图像模式(MRI)的解剖信息,并使用可学习的基础分布。此外,我们施加指南丢失和数据一致性丢失,以鼓励网络在保持高忠诚度的同时以高视觉质量生成图像。从25名高级神经胶质瘤患者获得的1H-MRSI数据集上进行的实验表明,我们的增强子网络的表现优于对抗网络和基线基线方法。我们的方法还允许视觉质量调整和不确定性估计。
translated by 谷歌翻译
在各种设备上部署深度学习模型已成为一个重要的话题。硬件专业化的浪潮为多维张量计算带来了一套多样化的加速度原始图。这些新的加速原始基原料以及新兴的机器学习模型带来了巨大的工程挑战。在本文中,我们提出了Tensorir,这是一种编译器抽象,用于通过这些张量计算原始素优化程序。Tensorir概括了现有机器学习编译器中使用的循环巢表示,以将张量计算作为一流的公民。最后,我们在抽象之上构建了一个端到端框架,以自动优化给定的张量计算原始图的深度学习模型。实验结果表明,Tensorir编译会自动使用给定硬件后端的张量计算原始图,并提供与跨平台的最新手工精制系统竞争性能的性能。
translated by 谷歌翻译
视觉任务中变形金刚的兴起不仅可以推进网络骨干设计,而且还启动了一个全新的页面,以实现端到端的图像识别(例如,对象检测和泛型分段)。源自自然语言处理(NLP)的变压器体系结构,包括自我注意力和交叉注意力,有效地学习了序列中元素之间的远距离相互作用。但是,我们观察到,大多数现有的基于变压器的视觉模型只是从NLP中借用了这个想法,忽略了语言和图像之间的关键差异,尤其是空间扁平的像素特征的极高序列长度。随后,这阻碍了像素特征和对象查询之间的交叉注意力学习。在本文中,我们重新考虑像素和对象查询之间的关系,并建议将交叉注意学习作为一个聚类过程进行重新重新制定。受传统K-均值聚类算法的启发,我们开发了K-Means面膜Xformer(Kmax-Deeplab)进行细分任务,这不仅可以改善最先进的艺术品,而且享有简单而优雅的设计。结果,我们的Kmax-Deeplab在Coco Val设置上以58.0%的PQ实现了新的最先进的性能,而CityScapes Val设置为68.4%PQ,44.0%AP和83.5%MIOU,而无需测试时间增加或外部数据集。我们希望我们的工作能够阐明设计为视觉任务量身定制的变压器。代码和型号可在https://github.com/google-research/deeplab2上找到
translated by 谷歌翻译
鲁棒性和准确性是工业检查的两个关键指标。在本文中,我们提出的基准可以评估结构化光方法的性能。我们的评估指标是从工厂中的许多检查任务中学习。我们提出的指标包括四个详细标准,例如平坦,长度,高度和球形。然后,我们可以判断是否可以通过我们的评估指标将结构化的光方法/设备应用于指定的检查任务。在最终实验部分中,通过我们的指标评估了用于打字针针检查性能的结构化轻型设备。
translated by 谷歌翻译
我们提出了聚类蒙版变压器(CMT-DeepLab),这是一种基于变压器的框架,用于围绕聚类设计的泛型分割。它重新考虑了用于分割和检测的现有变压器架构;CMT-DeepLab认为对象查询是群集中心,该中心填充了应用于分割时将像素分组的作用。群集通过交替的过程计算,首先通过其功能亲和力将像素分配给簇,然后更新集群中心和像素功能。这些操作共同包含聚类蒙版变压器(CMT)层,该层产生了越野器的交叉注意,并且与最终的分割任务更加一致。CMT-DeepLab在可可Test-DEV集中实现了55.7%的PQ的新最先进的PQ,可显着提高先前ART的性能。
translated by 谷歌翻译
Panoptic图像分割是计算机视觉任务,即在图像中查找像素组并为其分配语义类别和对象实例标识符。由于其在机器人技术和自动驾驶中的关键应用,图像细分的研究变得越来越流行。因此,研究社区依靠公开可用的基准数据集来推进计算机视觉中的最新技术。但是,由于将图像标记为高昂的成本,因此缺乏适合全景分割的公开地面真相标签。高标签成本还使得将现有数据集扩展到视频域和多相机设置是一项挑战。因此,我们介绍了Waymo Open DataSet:全景视频全景分割数据集,这是一个大型数据集,它提供了用于自主驾驶的高质量的全景分割标签。我们使用公开的Waymo打开数据集生成数据集,利用各种相机图像集。随着时间的推移,我们的标签是一致的,用于视频处理,并且在车辆上安装的多个摄像头保持一致,以了解全景的理解。具体而言,我们为28个语义类别和2,860个时间序列提供标签,这些标签由在三个不同地理位置驾驶的自动驾驶汽车上安装的五个摄像机捕获,从而导致总共标记为100k标记的相机图像。据我们所知,这使我们的数据集比现有的数据集大量数据集大的数量级。我们进一步提出了一个新的基准,用于全景视频全景分割,并根据DeepLab模型家族建立许多强大的基准。我们将公开制作基准和代码。在https://waymo.com/open上找到数据集。
translated by 谷歌翻译
多模式的预训练和知识发现是多模式机器学习中的两个重要研究主题。然而,没有现有的作品试图将知识发现与知识指导的多模式预训练联系起来。在本文中,我们建议将它们统一成一个连续的学习框架以进行相互改进。以图像和文本的开放域单模式数据集为输入,我们将知识图作为支持这两个任务的基础。对于知识发现,使用预训练的模型来识别图表上的跨模式链接。对于模型预训练,将知识图用作指导模型更新的外部知识。这两个步骤是在我们的持续学习框架中迭代执行的。关于知识发现和预训练模型,MS-Coco和FlickR30K的实验结果验证了我们框架的有效性。
translated by 谷歌翻译