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
Human modeling and relighting are two fundamental problems in computer vision and graphics, where high-quality datasets can largely facilitate related research. However, most existing human datasets only provide multi-view human images captured under the same illumination. Although valuable for modeling tasks, they are not readily used in relighting problems. To promote research in both fields, in this paper, we present UltraStage, a new 3D human dataset that contains more than 2K high-quality human assets captured under both multi-view and multi-illumination settings. Specifically, for each example, we provide 32 surrounding views illuminated with one white light and two gradient illuminations. In addition to regular multi-view images, gradient illuminations help recover detailed surface normal and spatially-varying material maps, enabling various relighting applications. Inspired by recent advances in neural representation, we further interpret each example into a neural human asset which allows novel view synthesis under arbitrary lighting conditions. We show our neural human assets can achieve extremely high capture performance and are capable of representing fine details such as facial wrinkles and cloth folds. We also validate UltraStage in single image relighting tasks, training neural networks with virtual relighted data from neural assets and demonstrating realistic rendering improvements over prior arts. UltraStage will be publicly available to the community to stimulate significant future developments in various human modeling and rendering tasks.
translated by 谷歌翻译
Object goal navigation (ObjectNav) in unseen environments is a fundamental task for Embodied AI. Agents in existing works learn ObjectNav policies based on 2D maps, scene graphs, or image sequences. Considering this task happens in 3D space, a 3D-aware agent can advance its ObjectNav capability via learning from fine-grained spatial information. However, leveraging 3D scene representation can be prohibitively unpractical for policy learning in this floor-level task, due to low sample efficiency and expensive computational cost. In this work, we propose a framework for the challenging 3D-aware ObjectNav based on two straightforward sub-policies. The two sub-polices, namely corner-guided exploration policy and category-aware identification policy, simultaneously perform by utilizing online fused 3D points as observation. Through extensive experiments, we show that this framework can dramatically improve the performance in ObjectNav through learning from 3D scene representation. Our framework achieves the best performance among all modular-based methods on the Matterport3D and Gibson datasets, while requiring (up to 30x) less computational cost for training.
translated by 谷歌翻译
近年来,在自学学习(SSL)方面取得了重大成功,这有助于各种下游任务。但是,攻击者可能会窃取此类SSL模型并将其商业化以获利,这对于保护其知识产权(IP)至关重要。大多数现有的IP保护解决方案都是为监督学习模型而设计的,不能直接使用,因为它们要求模型的下游任务和目标标签在水印嵌入过程中已知并获得,这在SSL的域中并非总是可以的。为了解决此类问题,尤其是在水印嵌入过程中下游任务多样化且未知时,我们提出了一种新型的黑盒水印解决方案,名为SSL-WM,以保护SSL模型的所有权。 SSL-WM将水印编码器的水印输入映射到不变的表示空间中,该空间会导致任何下游分类器产生预期的行为,从而允许检测到嵌入式水印。我们使用不同的SSL模型(包括基于对比度和基于生成的生成型)来评估许多任务,例如计算机视觉(CV)和自然语言处理(NLP)等许多任务。实验结果表明,SSL-WM可以有效地验证各种下游任务中被盗SSL模型的所有权。此外,SSL-WM对模型进行微调和修剪攻击非常强大。最后,SSL-WM还可以从评估的水印检测方法中逃避检测,从而证明了其在保护SSL模型IP时的有希望的应用。
translated by 谷歌翻译
联合学习(FL)使参与方能够在不公开私人数据信息的情况下协作建立一个全球模型。必须采用适当的保护机制,以满足保留\ textit {privacy}并维护高模型\ textit {utility}的相反要求。此外,为了实现大规模的模型培训和部署,联合学习系统实现高\ textit {效率}是一项任务。我们提出了一个统一的联合学习框架,可以调和水平和垂直的联合学习。基于此框架,我们制定和量化了隐私泄漏,公用事业损失和降低效率之间的权衡,这使我们成为了联合学习系统的无午餐定理(NFL)定理。 NFL表示,期望FL算法同时在某些情况下同时提供出色的隐私,实用性和效率是不现实的。然后,我们分析了几种广泛补习的保护机制的隐私泄漏,效用损失和效率降低的下限,包括\ textit {Randomization},\ textIt {同粒子加密},\ textit {secretit {secret {sertial {sertion {sertion {compression} {Compression}。我们的分析可以作为选择保护参数以满足特定要求的指南。
translated by 谷歌翻译
在整个2019年冠状病毒疾病(COVID-19)大流行中,决策者依靠预测模型来确定和实施非药物干预措施(NPI)。在构建预测模型时,需要从包括开发人员,分析师和测试人员在内的各种利益相关者进行不断更新的数据集,以提供精确的预测。在这里,我们报告了可扩展管道的设计,该管道可作为数据同步,以支持国际自上而下的时空时空观察和covid-19的预测模型,名为Where2test,用于德国,捷克西亚和波兰。我们已经使用PostgreSQL构建了一个操作数据存储(ODS),以连续合并多个数据源的数据集,执行协作工作,促进高性能数据分析和跟踪更改。 ODS不仅是为了存储来自德国,捷克和波兰的COVID-19数据,而且还存储了其他领域。元数据的模式采用维数事实模型,能够同步这些区域的各种数据结构,并且可以扩展到整个世界。接下来,使用批处理,转移和负载(ETL)作业填充ODS。随后创建了SQL查询,以减少为用户预处理数据的需求。然后,数据不仅可以支持使用版本控制的Arima-Holt模型和其他分析来预测,以支持决策制定,还可以风险计算器和优化应用程序。数据同步以每天的间隔运行,该间隔显示在https://www.where2test.de上。
translated by 谷歌翻译
对接系统对于在线多人游戏中创建公平匹配至关重要,这直接影响玩家的满足感和游戏体验。大多数对接系统在很大程度上取决于对玩家游戏技能的精确估计来构建公平的游戏。但是,新手的技能等级通常是不准确的,因为当前的对接评级算法需要大量游戏才能学习新玩家的真正技能。在早期阶段使用这些不可靠的技能得分通常会导致团队绩效方面的差异,这会导致负面的游戏体验。这被称为对接评级算法的“冷启动”问题。为了克服这个难题,本文提出了QuickSkill,这是一个基于深度学习的新手技能估算框架,以快速探究在线多人游戏中新玩家的能力。 QuickSkill提取了玩家最初的几款游戏中的顺序性能功能,以通过专用的神经网络来预测他/她的未来技能评级,从而在玩家的早期游戏阶段进行准确的技能估计。通过使用Quickskill进行对接,可以在最初的冷门时期大大改善游戏公平性。我们在离线和在线场景中都在流行的移动多人游戏中进行实验。使用两个现实世界中的匿名游戏数据集获得的结果表明,提议的QuickSkill提供了对新手游戏技能的精确估计,从而导致团队技能差异明显降低和更好的玩家游戏体验。据我们所知,提议的Quickskill是第一个解决传统技能评级算法的冷门问题的框架。
translated by 谷歌翻译
本文为旋转组开发了旋转不变的阵阵卷积,因此(3)可以提炼球形信号的多尺度信息。球形的阵头变换从$ \ mathbb {s}^2 $推广到SO(3)组,该组通过一组紧密的Framelet操作员将球形信号分解为近似和详细的光谱系数。分解和重建过程中的球形信号实现了旋转不变性。基于阵型变换,我们形成了一个带有多个SO(3)一面卷积层的NEDLET近似均值球形CNN(NES)。该网络建立了一个强大的工具,可以提取球形信号的几何不变特征。该模型允许具有多分辨率表示的足够网络可伸缩性。通过小波收缩激活函数学习了强大的信号嵌入,该函数会过滤冗余高通表示,同时保持近似旋转不变性。 NES实现了量子化学回归和宇宙微波背景(CMB)的最新性能,删除重建,这显示了通过高分辨率和多尺度球形信号表示解决科学挑战的巨大潜力。
translated by 谷歌翻译
规则集是高度可解释的逻辑模型,其中决策的谓词以分离的正常形式(DNF或ands)表达,或者等效地,总体模型包括无序的决策规则集合。在本文中,我们考虑了一种基于基于学习规则集的基于superdular优化的方法。学习问题被构成一个子集选择任务,其中所有可能的规则的子集需要选择以形成准确且可解释的规则集。我们采用了表现出表达性的目标函数,因此可以适合于次管的优化技术。为了克服难以处理指数尺寸的地面规则集的难度,搜索规则的子问题被抛弃为另一个询问特征子集的子集选择任务。我们表明,可以为子问题编写诱导的目标函数,作为两个子模函数(DS)函数的差,以使其通过DS优化算法近似解决。总体而言,所提出的方法是简单,可扩展的,并且可能会从进一步研究子解体优化中受益。实际数据集上的实验证明了我们方法的有效性。
translated by 谷歌翻译
视频修复旨在从多个低质量框架中恢复多个高质量的帧。现有的视频修复方法通常属于两种极端情况,即它们并行恢复所有帧,或者以复发方式恢复视频框架,这将导致不同的优点和缺点。通常,前者具有时间信息融合的优势。但是,它遭受了较大的模型尺寸和密集的内存消耗;后者的模型大小相对较小,因为它在跨帧中共享参数。但是,它缺乏远程依赖建模能力和并行性。在本文中,我们试图通过提出经常性视频恢复变压器(即RVRT)来整合两种情况的优势。 RVRT在全球经常性的框架内并行处理本地相邻框架,该框架可以在模型大小,有效性和效率之间实现良好的权衡。具体而言,RVRT将视频分为多个剪辑,并使用先前推断的剪辑功能来估计后续剪辑功能。在每个剪辑中,通过隐式特征聚合共同更新不同的帧功能。在不同的剪辑中,引导的变形注意力是为剪辑对齐对齐的,该剪辑对齐可预测整个推断的夹子中的多个相关位置,并通过注意机制汇总其特征。关于视频超分辨率,DeBlurring和DeNoising的广泛实验表明,所提出的RVRT在具有平衡模型大小,测试内存和运行时的基准数据集上实现了最先进的性能。
translated by 谷歌翻译