背景。通常,深度神经网络(DNN)概括了从类似于训练集的分布的样本概括。然而,当测试样本从不同的分布中抽出时,DNNS的预测是脆性和不可靠的。这是在现实世界应用中部署的主要关注点,这种行为可能以相当大的成本,例如工业生产线,自治车辆或医疗保健应用。贡献。我们将DNN中的分布(OOD)检测出来作为统计假设检测问题。在我们所提出的框架内产生的测试将证据组合来自整个网络。与以前的检测启发式不同,此框架返回每个测试样本的$ p $ -value。有保证维护I型错误(T1E - 错误地识别OOD样本为ID)进行测试数据。此外,这允许在保持T1E的同时组合多个检测器。在此框架上建立,我们建议一种基于低阶统计数据的新型程序。我们的方法在不接受的EOD基准上的最新方法实现了比较或更好的结果,而无需再培训网络参数或假设测试分配的现有知识 - 并且以计算成本的一小部分。
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
Many visualization techniques have been created to help explain the behavior of convolutional neural networks (CNNs), but they largely consist of static diagrams that convey limited information. Interactive visualizations can provide more rich insights and allow users to more easily explore a model's behavior; however, they are typically not easily reusable and are specific to a particular model. We introduce Visual Feature Search, a novel interactive visualization that is generalizable to any CNN and can easily be incorporated into a researcher's workflow. Our tool allows a user to highlight an image region and search for images from a given dataset with the most similar CNN features. It supports searching through large image datasets with an efficient cache-based search implementation. We demonstrate how our tool elucidates different aspects of model behavior by performing experiments on supervised, self-supervised, and human-edited CNNs. We also release a portable Python library and several IPython notebooks to enable researchers to easily use our tool in their own experiments. Our code can be found at https://github.com/lookingglasslab/VisualFeatureSearch.
translated by 谷歌翻译
Bayesian Optimization is a useful tool for experiment design. Unfortunately, the classical, sequential setting of Bayesian Optimization does not translate well into laboratory experiments, for instance battery design, where measurements may come from different sources and their evaluations may require significant waiting times. Multi-fidelity Bayesian Optimization addresses the setting with measurements from different sources. Asynchronous batch Bayesian Optimization provides a framework to select new experiments before the results of the prior experiments are revealed. This paper proposes an algorithm combining multi-fidelity and asynchronous batch methods. We empirically study the algorithm behavior, and show it can outperform single-fidelity batch methods and multi-fidelity sequential methods. As an application, we consider designing electrode materials for optimal performance in pouch cells using experiments with coin cells to approximate battery performance.
translated by 谷歌翻译
使用计算机视觉对间接费用的分析是一个问题,在学术文献中受到了很大的关注。在这个领域运行的大多数技术都非常专业,需要大型数据集的昂贵手动注释。这些问题通过开发更通用的框架来解决这些问题,并结合了表示学习的进步,该框架可以更灵活地分析具有有限标记数据的新图像类别。首先,根据动量对比机制创建了未标记的空中图像数据集的强大表示。随后,通过构建5个标记图像的准确分类器来专门用于不同的任务。从6000万个未标记的图像中,成功的低水平检测城市基础设施进化,体现了我们推进定量城市研究的巨大潜力。
translated by 谷歌翻译
基于概念的解释性方法旨在使用一组预定义的语义概念来解释深度神经网络模型的预测。这些方法在新的“探针”数据集上评估了训练有素的模型,并将模型预测与该数据集中标记的视觉概念相关联。尽管他们受欢迎,但他们的局限性并未被文献所理解和阐明。在这项工作中,我们分析了基于概念的解释中的三个常见因素。首先,选择探针数据集对生成的解释有深远的影响。我们的分析表明,不同的探针数据集可能会导致非常不同的解释,并表明这些解释在探针数据集之外不可概括。其次,我们发现探针数据集中的概念通常比他们声称要解释的课程更不太明显,更难学习,这使解释的正确性提出了质疑。我们认为,仅在基于概念的解释中才能使用视觉上的显着概念。最后,尽管现有方法使用了数百甚至数千个概念,但我们的人类研究揭示了32个或更少的概念更严格的上限,除此之外,这些解释实际上不太有用。我们对基于概念的解释性方法的未来发展和分析提出建议。可以在\ url {https://github.com/princetonvisualai/overlookedfactors}找到我们的分析和用户界面的代码。
translated by 谷歌翻译
Tree Ensembles可以非常适合黑盒优化任务,例如算法调整和神经体系结构搜索,因为它们在几乎没有手动调整的情况下实现了良好的预测性能,自然可以处理离散的功能空间,并且对培训中的异常值相对不敏感数据。在使用树的组合进行黑盒优化方面面临的两个众所周知的挑战是(i)有效地量化模型的不确定性,以进行探索,以及(ii)优化在零件的恒定采集函数上。为了同时解决这两个点,我们建议在获得模型方差估计之前使用树的内核解释为高斯过程,并为采集函数开发兼容的优化公式。后者进一步使我们能够通过考虑工程设置中的域知识和建模搜索空间对称性,例如神经体系结构搜索中的层次结构关系,从而无缝整合已知约束,以提高采样效率。我们的框架以及最先进的方法以及对连续/离散功能的不受限制的黑框优化,并且优于结合混合变量特征空间和已知输入约束的问题的竞争方法。
translated by 谷歌翻译
机器学习(ML)是人工智能(AI)的子场,其放射学中的应用正在以不断加速的速度增长。研究最多的ML应用程序是图像的自动解释。但是,可以将自然语言处理(NLP)与文本解释任务组合的ML结合使用,在放射学中也具有许多潜在的应用。一种这样的应用是放射学原始胶体的自动化,涉及解释临床放射学转介并选择适当的成像技术。这是一项必不可少的任务,可确保执行正确的成像。但是,放射科医生必须将专门用于原始胶片的时间进行报告,与推荐人或教学进行报告,交流。迄今为止,很少有使用临床文本自动选择协议选择的ML模型的出版物。本文回顾了该领域的现有文献。参考机器学习公约建议的最佳实践对已发布模型进行系统评估。讨论了在临床环境中实施自动质胶的进展。
translated by 谷歌翻译
已知性别偏见存在于大规模的视觉数据集中,并且可以在下游模型中反映甚至扩大。许多先前的作品通常通过尝试从图像中删除性别表达信息来减轻性别偏见。为了理解这些方法的可行性和实用性,我们研究了大规模视觉数据集中存在的$ \ textit {gengender伪像} $。我们将$ \ textit {性别伪像} $定义为与性别相关的视觉提示,专门针对那些由现代图像分类器学习并具有可解释的人类推论的线索。通过我们的分析,我们发现性别伪像在可可和开放型数据集中无处不在,从低级信息(例如,颜色通道的平均值)到图像的高级组成(例如姿势和姿势和姿势,,,,,,,,,地和图像的平均值),无处不在(例如,姿势和姿势,姿势和姿势,,,姿势和姿势,是姿势和姿势,是姿势和姿势,是姿势和姿势的平均值)。人的位置)。鉴于性别文物的流行,我们声称试图从此类数据集中删除性别文物的尝试是不可行的。取而代之的是,责任在于研究人员和从业人员意识到数据集中图像的分布是高度性别的,因此开发了对各组之间这些分配变化的强大方法。
translated by 谷歌翻译
在过去的十年中,深度学习模型在机器学习的不同领域取得了巨大的成功。但是,这些模型的大小和复杂性使它们难以理解。为了使它们更容易解释,最近的一些作品着重于通过人类解剖的语义属性来解释深神网络的部分。但是,仅使用语义属性完全解释复杂的模型可能是不可能的。在这项工作中,我们建议使用一小部分无法解释的功能来增强这些属性。具体而言,我们开发了一个新颖的解释框架(通过标记和未标记分解的解释),将模型的预测分解为两个部分:一个可以通过语义属性的线性组合来解释,而另一部分则取决于未解释的功能。 。通过识别后者,我们能够分析模型的“无法解释的”部分,从而了解模型使用的信息。我们表明,一组未标记的功能可以推广到具有相同功能空间的多种型号,并将我们的作品与两种流行的面向属性的方法,可解释的基础分解和概念瓶颈进行比较,并讨论Elude提供的其他见解。
translated by 谷歌翻译