本文提供了在CVPR 2021会议上组织的讲习班*在CVPR 2021年会议上的创新应用中学到的伦理考虑因素,以及在ECCV的时尚,艺术和设计*的计算机愿景(ECCV)的一系列讲习班2018年,ICCV 2019年和CVPR 2020。我们希望这一反思将把艺术家和机器学习研究人员带入计算机视觉创造性应用的道德和社会方面的对话。
translated by 谷歌翻译
Aspect or query-based summarization has recently caught more attention, as it can generate differentiated summaries based on users' interests. However, the current dataset for aspect or query-based summarization either focuses on specific domains, contains relatively small-scale instances, or includes only a few aspect types. Such limitations hinder further explorations in this direction. In this work, we take advantage of crowd-sourcing knowledge on Wikipedia.org and automatically create a high-quality, large-scale open-domain aspect-based summarization dataset named OASum, which contains more than 3.7 million instances with around 1 million different aspects on 2 million Wikipedia pages. We provide benchmark results on OAsum and demonstrate its ability for diverse aspect-based summarization generation. To overcome the data scarcity problem on specific domains, we also perform zero-shot, few-shot, and fine-tuning on seven downstream datasets. Specifically, zero/few-shot and fine-tuning results show that the model pre-trained on our corpus demonstrates a strong aspect or query-focused generation ability compared with the backbone model. Our dataset and pre-trained checkpoints are publicly available.
translated by 谷歌翻译
The primary aim of this research was to find a model that best predicts which fallen angel bonds would either potentially rise up back to investment grade bonds and which ones would fall into bankruptcy. To implement the solution, we thought that the ideal method would be to create an optimal machine learning model that could predict bankruptcies. Among the many machine learning models out there we decided to pick four classification methods: logistic regression, KNN, SVM, and NN. We also utilized an automated methods of Google Cloud's machine learning. The results of our model comparisons showed that the models did not predict bankruptcies very well on the original data set with the exception of Google Cloud's machine learning having a high precision score. However, our over-sampled and feature selection data set did perform very well. This could likely be due to the model being over-fitted to match the narrative of the over-sampled data (as in, it does not accurately predict data outside of this data set quite well). Therefore, we were not able to create a model that we are confident that would predict bankruptcies. However, we were able to find value out of this project in two key ways. The first is that Google Cloud's machine learning model in every metric and in every data set either outperformed or performed on par with the other models. The second is that we found that utilizing feature selection did not reduce predictive power that much. This means that we can reduce the amount of data to collect for future experimentation regarding predicting bankruptcies.
translated by 谷歌翻译
We introduce a new benchmark dataset, Placenta, for node classification in an underexplored domain: predicting microanatomical tissue structures from cell graphs in placenta histology whole slide images. This problem is uniquely challenging for graph learning for a few reasons. Cell graphs are large (>1 million nodes per image), node features are varied (64-dimensions of 11 types of cells), class labels are imbalanced (9 classes ranging from 0.21% of the data to 40.0%), and cellular communities cluster into heterogeneously distributed tissues of widely varying sizes (from 11 nodes to 44,671 nodes for a single structure). Here, we release a dataset consisting of two cell graphs from two placenta histology images totalling 2,395,747 nodes, 799,745 of which have ground truth labels. We present inductive benchmark results for 7 scalable models and show how the unique qualities of cell graphs can help drive the development of novel graph neural network architectures.
translated by 谷歌翻译
这项研究旨在实现两个目标:第一个目标是策划一个大型且信息丰富的数据集,其中包含有关球员的行动和位置的关键和简洁的摘要,以及在专业和NCAA中排球的来回旅行模式Div-i室内排球游戏。尽管几项先前的研究旨在为其他运动创建类似的数据集(例如羽毛球和足球),但尚未实现为室内排球创建这样的数据集。第二个目标是引入排球描述性语言,以充分描述游戏中的集会过程并将语言应用于我们的数据集。基于精选的数据集和我们的描述性运动语言,我们使用我们的数据集介绍了三项用于自动化排球行动和战术分析的任务:(1)排球拉力赛预测,旨在预测集会的结果,并帮助球员和教练改善决策制定决策在实践中,(2)设置类型和命中类型预测,以帮助教练和球员更有效地为游戏做准备,以及(3)排球策略和进攻区统计,以提供高级排球统计数据,并帮助教练了解游戏和对手的策略更好的。我们进行了案例研究,以展示实验结果如何为排球分析社区提供见解。此外,基于现实世界数据的实验评估为我们的数据集和语言的未来研究和应用建立了基准。这项研究弥合了室内排球场与计算机科学之间的差距。
translated by 谷歌翻译
事件参数提取(EAE)在句子级别进行了很好的研究,但在文档级别进行了探索。在本文中,我们研究以捕获实际上分布在文档中的句子的事件论点。先前的工作主要假设对丰富的文档监督的完全访问,而忽略了该论点监督在文档中受到限制的事实。为了填补这一空白,我们基于最大的文档级事件提取数据集DOCEE提出了几个示波的文档级事件参数提取基准。我们首先定义了新问题,并通过新颖的N-Way-D-Doc采样而不是传统的NWay-K-shot策略来重建语料库。然后,我们将高级文档级神经模型调整为几个弹出设置,以在内部和跨域设置下提供基线结果。由于参数提取取决于多个句子的上下文,并且学习过程仅限于很少的示例,因此我们发现该任务在实质上较低的性能中非常具有挑战性。考虑到很少有Docae与低资源制度下的实际使用密切相关,我们希望这种基准能够朝着这一方向发展进行更多的研究。我们的数据和代码将在线提供。
translated by 谷歌翻译
这项研究提出了新的策略,以研究信任和群体动态在儿童机器人相互作用中的相互影响。我们使用类人机器人ICUB实施了类似游戏的实验活动,并设计了一份问卷来评估孩子如何看待这种相互作用。我们还旨在验证传感器,设置和任务是否适合研究此类方面。问卷的结果表明,年轻人将ICUB视为朋友,通常以积极的方式将ICUB视为朋友。其他初步结果表明,通常,孩子在活动期间信任ICUB,并且在其错误后,他们试图用诸如:“不用担心ICUB,我们原谅您”之类的句子来放心。此外,对机器人在小组认知活动中的信任似乎会根据性别而发生变化:在机器人连续两个错误之后,女孩倾向于比男孩更信任ICUB。最后,跨游戏计算的点和自我报告的量表之间的不同年龄组之间没有明显的差异。我们提出的工具适合研究不同年龄段的人类机器人相互作用(HRI)的信任,并且似乎适合理解小组相互作用的信任机制。
translated by 谷歌翻译
自我监督学习(SSL)通过利用不需要标签的借口任务来学习有用的归纳偏见。 SSL的未标记性质使得对整个幻灯片组织病理学图像(WSIS)尤为重要,在该图片级的人类注释很难。蒙面自动编码器(MAE)是一种适合数字病理学的SSL方法,因为它不需要阴性采样,并且几乎不需要数据增加。但是,自然图像和数字病理图像之间的域移动需要进一步研究贴片级WSIS的MA​​E。在本文中,我们研究了组织病理学中MAE的几种设计选择。此外,我们引入了一个多模式MAE(MMAE),该MAE(MMAE)利用了苏木精和曙红(H&E)染色的WSI的特定组成性。我们在公共补丁级数据集NCT-CRC-HE-100K上进行了实验。结果表明,MMAE架构的表现优于监督基线和其他最先进的SSL技术,用于八类组织表型任务,仅利用100个标记的样品进行微调。我们的代码可从https://github.com/wisdomikezogwo/mmae_pathology获得
translated by 谷歌翻译
人类语言中发现的最强大的模式之一是ZIPF的缩写定律,即更短的单词的趋势。自ZIPF开创性研究以来,该定律被视为压缩的体现,即形式的长度最小化 - 自然交流的普遍原则。尽管对语言进行优化的说法已经变得时尚,但衡量语言优化程度的尝试却相当稀缺。在这里,我们证明压缩在无例外的大量语言中表现出来,并且独立于测量单位。这两个单词长度都可以在书面语言的字符以及口语的持续时间中检测到。此外,为了衡量优化程度,我们得出了一个随机基线的简单公式,并提出了两个分数归一化的分数,即,它们相对于最小值和随机基线都进行了归一化。我们分析了这些和其他分数的理论和统计优势和缺点。利用最佳分数,我们首次量化了语言中单词长度的最佳程度。这表明当单词长度以字符测量时,语言平均被优化至62%或67%(取决于源),当单词长度及时测量时,平均而言,平均而言,平均而言,平均而言,平均而言,平均而言,平均至65%。通常,口语持续时间比字符中的书面单词长度更优化。除了这里报告的分析外,我们的工作还铺平了衡量其他物种发声或手势的最佳程度的方法,并将其与书面,口语或签名的人类语言进行比较。
translated by 谷歌翻译
神经网络具有充当通用函数近似器的能力,但它们不可解释,并且在其训练区域之外也不能概括。在尝试将标准神经普通微分方程(神经ODE)应用于动态系统时,这两个问题都是有问题的。我们介绍了多项式神经ODE,这是神经ode框架内部的深层神经网络。我们证明了多项式神经ODE的能力,可以预测训练区域外部,并在没有其他工具(例如Sindy)的情况下进行直接符号回归。
translated by 谷歌翻译