Unsupervised pre-training on millions of digital-born or scanned documents has shown promising advances in visual document understanding~(VDU). While various vision-language pre-training objectives are studied in existing solutions, the document textline, as an intrinsic granularity in VDU, has seldom been explored so far. A document textline usually contains words that are spatially and semantically correlated, which can be easily obtained from OCR engines. In this paper, we propose Wukong-Reader, trained with new pre-training objectives to leverage the structural knowledge nested in document textlines. We introduce textline-region contrastive learning to achieve fine-grained alignment between the visual regions and texts of document textlines. Furthermore, masked region modeling and textline-grid matching are also designed to enhance the visual and layout representations of textlines. Experiments show that our Wukong-Reader has superior performance on various VDU tasks such as information extraction. The fine-grained alignment over textlines also empowers Wukong-Reader with promising localization ability.
translated by 谷歌翻译
The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps.
translated by 谷歌翻译
Conventional cameras capture image irradiance on a sensor and convert it to RGB images using an image signal processor (ISP). The images can then be used for photography or visual computing tasks in a variety of applications, such as public safety surveillance and autonomous driving. One can argue that since RAW images contain all the captured information, the conversion of RAW to RGB using an ISP is not necessary for visual computing. In this paper, we propose a novel $\rho$-Vision framework to perform high-level semantic understanding and low-level compression using RAW images without the ISP subsystem used for decades. Considering the scarcity of available RAW image datasets, we first develop an unpaired CycleR2R network based on unsupervised CycleGAN to train modular unrolled ISP and inverse ISP (invISP) models using unpaired RAW and RGB images. We can then flexibly generate simulated RAW images (simRAW) using any existing RGB image dataset and finetune different models originally trained for the RGB domain to process real-world camera RAW images. We demonstrate object detection and image compression capabilities in RAW-domain using RAW-domain YOLOv3 and RAW image compressor (RIC) on snapshots from various cameras. Quantitative results reveal that RAW-domain task inference provides better detection accuracy and compression compared to RGB-domain processing. Furthermore, the proposed \r{ho}-Vision generalizes across various camera sensors and different task-specific models. Additional advantages of the proposed $\rho$-Vision that eliminates the ISP are the potential reductions in computations and processing times.
translated by 谷歌翻译
视觉导航要求代理商遵循自然语言说明以达到特定目标。可见的环境和看不见的环境之间的巨大差异使代理商概括良好的挑战。先前的研究提出了数据增强方法,以明确或隐式地减轻数据偏见并提供概括的改进。但是,他们试图记住增强的轨迹,并在测试时忽略在看不见的环境下的分布变化。在本文中,我们提出了一个看不见的差异,预期视力和语言导航(戴维斯),该差异通过鼓励测试时间的视觉一致性来概括为看不见的环境。具体来说,我们设计了:1)半监督框架戴维斯(Davis),该框架利用类似的语义观测来利用视觉一致性信号。 2)一个两阶段的学习程序,鼓励适应测试时间分布。该框架增强了模仿和强化学习的基本混合物与动量形成对比,以鼓励在联合训练阶段和测试时间适应阶段对类似观察的稳定决策。广泛的实验表明,戴维斯在R2R和RXR基准上实现了与先前最先进的VLN基线相比,取得了模型不合命源性的改进。我们的源代码和数据是补充材料。
translated by 谷歌翻译
在这项研究中,提出了一种集成检测模型,即Swin-Transformer-Yolov5或Swin-T-Yolov5,用于实时葡萄酒葡萄束检测,以继承Yolov5和Swin-Transformer的优势。该研究是针对2019年7月至9月的两种不同的霞多丽(始终白色或白色混合浆果皮肤)和梅洛(白色或白色混合浆果皮肤)的研究。从2019年7月至9月。 -yolov5,其性能与几个常用/竞争性对象探测器进行了比较,包括更快的R-CNN,Yolov3,Yolov4和Yolov5。在不同的测试条件下评估了所有模型,包括两个不同的天气条件(阳光和多云),两个不同的浆果成熟度(不成熟和成熟)以及三个不同的阳光方向/强度(早晨,中午和下午)进行全面比较。此外,Swin-t-Yolov5的预测葡萄束数量与地面真实值进行了比较,包括在注释过程中的现场手动计数和手动标记。结果表明,拟议的SWIN-T-YOLOV5的表现优于所有其他研究的葡萄束检测模型,当天气多云时,最高平均平均精度(MAP)和0.89的F1得分的97%。该地图分别比更快的R-CNN,Yolov3,Yolov4和Yolov5大约大约44%,18%,14%和4%。当检测到未成熟的浆果时,Swin-T-Yolov5获得了最低的地图(90%)和F1分数(0.82),其中该地图大约比相同的浆果大约40%,5%,3%和1%。此外,在将预测与地面真相进行比较时,Swin-T-Yolov5在Chardonnay品种上的表现更好,最多可达到R2的0.91和2.36根均方根误差(RMSE)。但是,它在Merlot品种上的表现不佳,仅达到R2和3.30的RMSE的0.70。
translated by 谷歌翻译
近年来,压缩图像超分辨率已引起了极大的关注,其中图像被压缩伪像和低分辨率伪影降解。由于复杂的杂化扭曲变形,因此很难通过简单的超分辨率和压缩伪像消除掉的简单合作来恢复扭曲的图像。在本文中,我们向前迈出了一步,提出了层次的SWIN变压器(HST)网络,以恢复低分辨率压缩图像,该图像共同捕获分层特征表示并分别用SWIN Transformer增强每个尺度表示。此外,我们发现具有超分辨率(SR)任务的预处理对于压缩图像超分辨率至关重要。为了探索不同的SR预审查的影响,我们将常用的SR任务(例如,比科比奇和不同的实际超分辨率仿真)作为我们的预处理任务,并揭示了SR在压缩的图像超分辨率中起不可替代的作用。随着HST和预训练的合作,我们的HST在AIM 2022挑战中获得了低质量压缩图像超分辨率轨道的第五名,PSNR为23.51db。广泛的实验和消融研究已经验证了我们提出的方法的有效性。
translated by 谷歌翻译
多模式学习,尤其是大规模的多模式预训练,在过去的几年中已经迅速发展,并带来了人工智能(AI)的最大进步。尽管具有有效性,但了解多模式预训练模型的潜在机制仍然是一个巨大的挑战。揭示此类模型的解释性可能会使AI领域中新型学习范式的突破。为此,鉴于人脑的多模式性质,我们建议借助非侵入性脑成像技术(例如功能磁共振成像(fMRI))探索多模式学习模型的解释性。具体而言,我们首先提出了1500万个图像文本对预训练的新设计的多模式基础模型,该模型在各种认知下游任务中显示出强烈的多模式理解和概括能力。此外,从神经编码的角度来看(基于我们的基础模型),我们发现,与单峰相比,经过多模式训练的视觉和舌编码器都更像脑状。特别是,我们确定了许多大脑区域,其中多模式训练的编码器表现出更好的神经编码性能。这与现有有关探索大脑多感觉整合的研究的发现是一致的。因此,我们认为,多模式基础模型是神经科学家研究人脑中多模式信号处理机制的更合适的工具。我们的发现还证明了多模式基础模型作为理想的计算模拟器的潜力,以促进脑和大脑的AI研究。
translated by 谷歌翻译
包含多种类型的节点和边缘的异质图在各种领域都普遍存在,包括书目网络,社交媒体和知识图。作为分析异质图的基本任务,相关度量旨在计算不同类型的两个对象之间的相关性,这些对象已在许多应用程序中使用,例如Web搜索,建议和社区检测。大多数现有的相关性措施都集中在对象具有相同类型的均质网络上,并为异质图制定了一些措施,但它们通常需要预定义的元路径。定义有意义的元路径需要大量的领域知识,这在很大程度上限制了其应用,尤其是在诸如知识图之类的图形富含模式的异质图上。最近,图形神经网络(GNN)已被广泛应用于许多图挖掘任务,但尚未用于测量相关性。为了解决上述问题,我们提出了一种基于GNN的新型相关性措施,即GSIM。具体而言,我们首先是理论上分析的,并表明GNN有效地测量图中节点的相关性。然后,我们建议基于上下文路径的图形神经网络(CP-GNN)自动利用异质图中的语义。此外,我们利用CP-GNN来支持任何类型的两个对象之间的相关性度量。广泛的实验表明,GSIM优于现有措施。
translated by 谷歌翻译
深度神经网络(DNN)在非参考图像质量评估(NR-IQA)方面具有巨大潜力。但是,NR-IQA的注释是劳动密集型且耗时的,这严重限制了其对真实图像的应用。为了减轻对质量注释的依赖,一些作品已将无监督的域适应性(UDA)应用于NR-IQA。但是,上述方法忽略了分类中使用的对齐空间是最佳选择,因为该空间不是为了感知而精心设计的。为了解决这一挑战,我们提出了一个有效的面向感知的无监督域适应方法,用于NR-IQA,该方法通过富含标签的源域数据将足够的知识转移到通过样式的对齐和混合的标签目标域图像。具体而言,我们发现了一个更紧凑,更可靠的空间,即基于有趣/惊人的观察结果,以感知为导向的UDA的特征样式空间,即DNN中深层的功能样式(即平均和差异)与DNN中的深层层完全相关NR-IQA的质量得分。因此,我们建议在更面向感知的空间(即特征样式空间)中对齐源和目标域,以减少其他质量 - Irretrelevant特征因素的干预措施。此外,为了提高质量得分与其功能样式之间的一致性,我们还提出了一种新颖的功能增强策略样式混音,将DNN的最后一层之前将功能样式(即平均值和差异)混合在一起,并混合使用标签。对两个典型的跨域设置(即合成至真实性和多种变形)的广泛实验结果证明了我们提出的styleam对NR-IQA的有效性。
translated by 谷歌翻译
近年来,由于它们在对点对点网络上的分散性学习问题(例如,多机构元学习,多机构的多方强化增强学习学习)上,分散的双层优化问题在网络和机器学习社区中引起了越来越多的关注。 ,个性化的培训和拜占庭的弹性学习)。但是,对于具有有限的计算和通信功能的对等网络上的分散式双层优化,如何实现低样本和通信复杂性是迄今为止尚未探索的两个基本挑战。在本文中,我们首次尝试研究了分别与外部和内部子问题相对应的非凸和强结构结构的分散双重优化问题。本文中我们的主要贡献是两倍:i)我们首先提出了一种称为Interact的确定性算法(Inter-gradient-descent-out-outer-tracked-gradeent),需要$ \ Mathcal {o}的样品复杂性(n \ epsilon) ^{ - 1})$和$ \ mathcal {o}的通信复杂性(\ epsilon^{ - 1})$解决双重优化问题,其中$ n $和$ \ epsilon> 0 $是样本的数量在每个代理和所需的平稳性差距上。 ii)为了放宽每次迭代中进行全面梯度评估的需求,我们提出了一个随机方差的互动版本(SVR Interact),该版本将样品复杂性提高到$ \ Mathcal {o}(\ sqrt {n} \ epsilon ^{ - 1})$在达到与确定算法相同的通信复杂性时。据我们所知,这项工作是第一个实现低样本和通信复杂性,以解决网络上的分散双层优化问题。我们的数值实验也证实了我们的理论发现。
translated by 谷歌翻译