The well-documented presence of texture bias in modern convolutional neural networks has led to a plethora of algorithms that promote an emphasis on shape cues, often to support generalization to new domains. Yet, common datasets, benchmarks and general model selection strategies are missing, and there is no agreed, rigorous evaluation protocol. In this paper, we investigate difficulties and limitations when training networks with reduced texture bias. In particular, we also show that proper evaluation and meaningful comparisons between methods are not trivial. We introduce BiasBed, a testbed for texture- and style-biased training, including multiple datasets and a range of existing algorithms. It comes with an extensive evaluation protocol that includes rigorous hypothesis testing to gauge the significance of the results, despite the considerable training instability of some style bias methods. Our extensive experiments, shed new light on the need for careful, statistically founded evaluation protocols for style bias (and beyond). E.g., we find that some algorithms proposed in the literature do not significantly mitigate the impact of style bias at all. With the release of BiasBed, we hope to foster a common understanding of consistent and meaningful comparisons, and consequently faster progress towards learning methods free of texture bias. Code is available at https://github.com/D1noFuzi/BiasBed
translated by 谷歌翻译
世界上最大的可可生产国C \^ote d'Ivoire and Ghana占全球可可生产的三分之二。在这两个国家,可可都是多年生作物,为近200万农民提供收入。然而,缺少可可种植区域的精确地图,阻碍了保护区,生产和产量的准确量化,并限制了可用于改善可持续性治理的信息。在这里,我们将可可种植园数据与公开可用的卫星图像结合在深度学习框架中,并为两国的可可种植园创建高分辨率地图,并被现场验证。我们的结果表明,可可栽培是C \^ote d'Ivoire和Ghane的保护区中森林损失的37%以上和13%的潜在驱动因素,该官员报告大大低估了种植的地区,最高40%在加纳。这些地图是提高可可生产地区保护和经济发展的关键基础。
translated by 谷歌翻译
AASM准则是为了有一种常用的方法,旨在标准化睡眠评分程序的数十年努力的结果。该指南涵盖了从技术/数字规格(例如,推荐的EEG推导)到相应的详细睡眠评分规则到年龄的几个方面。在睡眠评分自动化的背景下,与许多其他技术相比,深度学习表现出更好的性能。通常,临床专业知识和官方准则对于支持自动睡眠评分算法在解决任务时至关重要。在本文中,我们表明,基于深度学习的睡眠评分算法可能不需要充分利用临床知识或严格遵循AASM准则。具体而言,我们证明了U-Sleep是一种最先进的睡眠评分算法,即使使用临床非申请或非规定派生,也可以解决得分任务,即使无需利用有关有关的信息,也无需利用有关有关的信息。受试者的年代年龄。我们最终加强了一个众所周知的发现,即使用来自多个数据中心的数据始终导致与单个队列上的培训相比,可以使性能更好。确实,我们表明,即使增加了单个数据队列的大小和异质性,后者仍然有效。在我们的所有实验中,我们使用了来自13个不同临床研究的28528多个多摄影研究研究。
translated by 谷歌翻译
在不完整的数据集中对样本进行分类是机器学习从业人员的普遍目的,但并非平凡。在大多数现实世界数据集中发现缺失的数据,这些缺失值通常是使用已建立的方法估算的,然后进行分类现在完成,估算的样本。然后,机器学习研究人员的重点是优化下游分类性能。在这项研究中,我们强调必须考虑插补的质量。我们展示了如何评估质量的常用措施有缺陷,并提出了一类新的差异评分,这些分数着重于该方法重新创建数据的整体分布的程度。总而言之,我们强调了使用不良数据训练的分类器模型的可解释性损害。
translated by 谷歌翻译
语言模型既展示了定量的改进,又展示了新的定性功能,随着规模的增加。尽管它们具有潜在的变革性影响,但这些新能力的特征却很差。为了为未来的研究提供信息,为破坏性的新模型能力做准备,并改善社会有害的效果,至关重要的是,我们必须了解目前和近乎未来的能力和语言模型的局限性。为了应对这一挑战,我们介绍了超越模仿游戏基准(Big Bench)。 Big Bench目前由204个任务组成,由132家机构的442位作者贡献。任务主题是多样的,从语言学,儿童发展,数学,常识性推理,生物学,物理学,社会偏见,软件开发等等。 Big-Bench专注于被认为超出当前语言模型的功能的任务。我们评估了OpenAI的GPT型号,Google内部密集变压器体系结构和大型基础上的开关稀疏变压器的行为,跨越了数百万到数十亿个参数。此外,一个人类专家评估者团队执行了所有任务,以提供强大的基准。研究结果包括:模型性能和校准都随规模改善,但绝对的术语(以及与评估者的性能相比);在模型类中的性能非常相似,尽管带有稀疏性。逐渐和预测的任务通常涉及大量知识或记忆成分,而在临界规模上表现出“突破性”行为的任务通常涉及多个步骤或组成部分或脆性指标;社交偏见通常会随着含糊不清的环境而随着规模而增加,但这可以通过提示来改善。
translated by 谷歌翻译
The ability to estimate epistemic uncertainty is often crucial when deploying machine learning in the real world, but modern methods often produce overconfident, uncalibrated uncertainty predictions. A common approach to quantify epistemic uncertainty, usable across a wide class of prediction models, is to train a model ensemble. In a naive implementation, the ensemble approach has high computational cost and high memory demand. This challenges in particular modern deep learning, where even a single deep network is already demanding in terms of compute and memory, and has given rise to a number of attempts to emulate the model ensemble without actually instantiating separate ensemble members. We introduce FiLM-Ensemble, a deep, implicit ensemble method based on the concept of Feature-wise Linear Modulation (FiLM). That technique was originally developed for multi-task learning, with the aim of decoupling different tasks. We show that the idea can be extended to uncertainty quantification: by modulating the network activations of a single deep network with FiLM, one obtains a model ensemble with high diversity, and consequently well-calibrated estimates of epistemic uncertainty, with low computational overhead in comparison. Empirically, FiLM-Ensemble outperforms other implicit ensemble methods, and it and comes very close to the upper bound of an explicit ensemble of networks (sometimes even beating it), at a fraction of the memory cost.
translated by 谷歌翻译
Recently developed methods for video analysis, especially models for pose estimation and behavior classification, are transforming behavioral quantification to be more precise, scalable, and reproducible in fields such as neuroscience and ethology. These tools overcome long-standing limitations of manual scoring of video frames and traditional "center of mass" tracking algorithms to enable video analysis at scale. The expansion of open-source tools for video acquisition and analysis has led to new experimental approaches to understand behavior. Here, we review currently available open-source tools for video analysis and discuss how to set up these methods for labs new to video recording. We also discuss best practices for developing and using video analysis methods, including community-wide standards and critical needs for the open sharing of datasets and code, more widespread comparisons of video analysis methods, and better documentation for these methods especially for new users. We encourage broader adoption and continued development of these tools, which have tremendous potential for accelerating scientific progress in understanding the brain and behavior.
translated by 谷歌翻译
深度学习模式和地球观察的协同组合承诺支持可持续发展目标(SDGS)。新的发展和夸张的申请已经在改变人类将面临生活星球挑战的方式。本文审查了当前对地球观测数据的最深入学习方法,以及其在地球观测中深度学习的快速发展受到影响和实现最严重的SDG的应用。我们系统地审查案例研究至1)实现零饥饿,2)可持续城市,3)提供保管安全,4)减轻和适应气候变化,5)保留生物多样性。关注重要的社会,经济和环境影响。提前令人兴奋的时期即将到来,算法和地球数据可以帮助我们努力解决气候危机并支持更可持续发展的地方。
translated by 谷歌翻译
数据增强是自然语言处理(NLP)模型的鲁棒性评估的重要组成部分,以及增强他们培训的数据的多样性。在本文中,我们呈现NL-Cogmenter,这是一种新的参与式Python的自然语言增强框架,它支持创建两个转换(对数据的修改)和过滤器(根据特定功能的数据拆分)。我们描述了框架和初始的117个变换和23个过滤器,用于各种自然语言任务。我们通过使用其几个转换来分析流行自然语言模型的鲁棒性来证明NL-Upmenter的功效。基础架构,Datacards和稳健性分析结果在NL-Augmenter存储库上公开可用(\ url {https://github.com/gem-benchmark/nl-augmenter})。
translated by 谷歌翻译
以知情方式监测和管理地球林是解决生物多样性损失和气候变化等挑战的重要要求。虽然森林评估的传统或空中运动提供了在区域一级分析的准确数据,但将其扩展到整个国家,以外的高度分辨率几乎不可能。在这项工作中,我们提出了一种贝叶斯深度学习方法,以10米的分辨率为全国范围的森林结构变量,使用自由可用的卫星图像作为输入。我们的方法将Sentinel-2光学图像和Sentinel-1合成孔径雷达图像共同变换为五种不同的森林结构变量的地图:95th高度百分位,平均高度,密度,基尼系数和分数盖。我们从挪威的41个机载激光扫描任务中培训和测试我们的模型,并证明它能够概括取消测试区域,从而达到11%和15%之间的归一化平均值误差,具体取决于变量。我们的工作也是第一个提出贝叶斯深度学习方法的工作,以预测具有良好校准的不确定性估计的森林结构变量。这些提高了模型的可信度及其适用于需要可靠的信心估计的下游任务,例如知情决策。我们提出了一组广泛的实验,以验证预测地图的准确性以及预测的不确定性的质量。为了展示可扩展性,我们为五个森林结构变量提供挪威地图。
translated by 谷歌翻译