自驾驶车辆是交通的未来。凭借目前的进步,世界正在越来越靠近安全道路,几乎缺点且具有意外和消除人类错误的可能性。然而,仍有许多研究和开发能够达到稳健程度。一个重要方面是要了解一个完全包括所有细节的场景。作为场景中对象的某些特征(属性)(例如,例如,驱动程序行为)可能是正确的决策。然而,当前算法遭受具有如此丰富的属性的低质量数据集。因此,在本文中,我们为属性识别提供了一个新的数据集 - CityCapes属性识别(CAR)。新数据集通过添加每个图像中的对象属性的其他还有重要的注释层来扩展众所周知的DataSet CounsOce。目前,我们已经注释了超过32K的各类类别(车辆,行人等)。数据集具有结构化和量身定制的分类系统,其中每个类别都有自己的一组可能的属性。量身定制的分类学专注于为开发更好的自动驾驶算法而具有最具利益的属性,这些算法取决于准确的计算机视觉和现场理解。我们还为数据集创建了一个API,以简化汽车的使用。可以通过https://github.com/kareem-molwaly/car-api访问API。
translated by 谷歌翻译
尽管最先进的物体检测方法显示出令人信服的性能,但模型通常对对抗的攻击和分发数据不稳健。我们介绍了一个新的数据集,天然对手对象(Nao),以评估物体检测模型的稳健性。 Nao包含7,934个图像和9,943个对象,这些对象未经修改,代表了现实世界的情景,但导致最先进的检测模型以高信任误入歧途。与标准MSCOCO验证集相比,在NAO上评估时,高效的平均平均精度(MAP)降低74.5%。此外,通过比较各种对象检测架构,我们发现Mscoco验证集上的更好性能不一定转化为NAO的更好性能,这表明不能通过培训更准确的模型来简单地实现鲁棒性。我们进一步调查为什么NA​​O中难以检测和分类的原因。洗牌图像贴片的实验表明,模型对局部质地过于敏感。此外,使用集成梯度和背景替换,我们发现检测模型依赖于边界框内的像素信息,并且在预测类标签时对背景上下文不敏感。 Nao可以在https://drive.google.com/drive/folders/15p8sowojku6sseihlets86orfytgezi8下载。
translated by 谷歌翻译
We present the Group Propagation Vision Transformer (GPViT): a novel nonhierarchical (i.e. non-pyramidal) transformer model designed for general visual recognition with high-resolution features. High-resolution features (or tokens) are a natural fit for tasks that involve perceiving fine-grained details such as detection and segmentation, but exchanging global information between these features is expensive in memory and computation because of the way self-attention scales. We provide a highly efficient alternative Group Propagation Block (GP Block) to exchange global information. In each GP Block, features are first grouped together by a fixed number of learnable group tokens; we then perform Group Propagation where global information is exchanged between the grouped features; finally, global information in the updated grouped features is returned back to the image features through a transformer decoder. We evaluate GPViT on a variety of visual recognition tasks including image classification, semantic segmentation, object detection, and instance segmentation. Our method achieves significant performance gains over previous works across all tasks, especially on tasks that require high-resolution outputs, for example, our GPViT-L3 outperforms Swin Transformer-B by 2.0 mIoU on ADE20K semantic segmentation with only half as many parameters. Code and pre-trained models are available at https://github.com/ChenhongyiYang/GPViT .
translated by 谷歌翻译
We study the classic facility location setting, where we are given $n$ clients and $m$ possible facility locations in some arbitrary metric space, and want to choose a location to build a facility. The exact same setting also arises in spatial social choice, where voters are the clients and the goal is to choose a candidate or outcome, with the distance from a voter to an outcome representing the cost of this outcome for the voter (e.g., based on their ideological differences). Unlike most previous work, we do not focus on a single objective to optimize (e.g., the total distance from clients to the facility, or the maximum distance, etc.), but instead attempt to optimize several different objectives simultaneously. More specifically, we consider the $l$-centrum family of objectives, which includes the total distance, max distance, and many others. We present tight bounds on how well any pair of such objectives (e.g., max and sum) can be simultaneously approximated compared to their optimum outcomes. In particular, we show that for any such pair of objectives, it is always possible to choose an outcome which simultaneously approximates both objectives within a factor of $1+\sqrt{2}$, and give a precise characterization of how this factor improves as the two objectives being optimized become more similar. For $q>2$ different centrum objectives, we show that it is always possible to approximate all $q$ of these objectives within a small constant, and that this constant approaches 3 as $q\rightarrow \infty$. Our results show that when optimizing only a few simultaneous objectives, it is always possible to form an outcome which is a significantly better than 3 approximation for all of these objectives.
translated by 谷歌翻译
In order to assist the drug discovery/development process, pharmaceutical companies often apply biomedical NER and linking techniques over internal and public corpora. Decades of study of the field of BioNLP has produced a plethora of algorithms, systems and datasets. However, our experience has been that no single open source system meets all the requirements of a modern pharmaceutical company. In this work, we describe these requirements according to our experience of the industry, and present Kazu, a highly extensible, scalable open source framework designed to support BioNLP for the pharmaceutical sector. Kazu is a built around a computationally efficient version of the BERN2 NER model (TinyBERN2), and subsequently wraps several other BioNLP technologies into one coherent system. KAZU framework is open-sourced: https://github.com/AstraZeneca/KAZU
translated by 谷歌翻译
成功的材料选择对于设计和制造产品的设计自动化至关重要。设计师通过通过性能,制造性和可持续性评估选择最合适的材料来利用他们的知识和经验来创建高质量的设计。智能工具可以通过提供从先前的设计中学到的建议来帮助具有不同专业知识的设计师。为了实现这一目标,我们介绍了一个图表表示学习框架,该框架支持组装中身体的物质预测。我们将材料选择任务作为节点级预测任务,对CAD模型的汇编图表示,并使用图形神经网络(GNN)对其进行处理。在Fusion 360画廊数据集上执行的三个实验协议的评估表明我们的方法的可行性,达到了0.75 TOP-3 Micro-F1分数。提出的框架可以扩展到大型数据集,并将设计师的知识纳入学习过程。这些功能使该框架可以作为设计自动化的推荐系统以及未来工作的基准,从而缩小了人类设计师与智能设计代理之间的差距。
translated by 谷歌翻译
Systems Biology试图创建生物系统的数学模型,以减少固有的生物学复杂性,并为治疗性开发等应用提供预测。但是,确定哪种数学模型正确以及如何最佳地到达答案仍然是一个挑战。我们提出了一种使用系统生物学和可能性无推理方法的数学模型选择自动生物学模型选择的算法。我们的算法显示,在实验生物学和随机搜索中使用的常规启发式方法的先验信息中,在正确的模型中表现出了改善的性能。该方法显示有望加速生物基础科学和药物发现。
translated by 谷歌翻译
可以与其他代理人互动以完成给定任务的自主代理的发展是人工智能和机器学习研究的核心领域。为了实现这一目标,自主代理研究小组开发了用于自主系统控制的新型机器学习算法,特别关注深度强化学习和多代理强化学习。研究问题包括可扩展的协调代理政策和代理间沟通;从有限观察的情况下对其他代理的行为,目标和组成的推理;以及基于内在动机,课程学习,因果推断和代表性学习的样品学习。本文概述了该小组正在进行的研究组合,并讨论了未来方向的开放问题。
translated by 谷歌翻译
临时团队合作(AHT)是创建一个必须与以前看不见的队友合作而没有事先协调的问题。许多现有的AHT方法可以归类为基于类型的方法,这些方法需要一组预定义的队友进行培训。为训练设计队友类型是一个具有挑战性的问题,它决定了在训练期间与队友类型打交道时的代理商的概括性能。在这项工作中,我们提出了一种基于最大化最佳响应多样性指标的不同队友类型的方法。我们表明,我们提出的方法会产生队友类型,这些类型需要在协作期间从学习者那里获得更广泛的最佳反应,这可能会提高学习者在AHT中的稳健性与替代方法相比。
translated by 谷歌翻译
现实世界的行为通常是由多种代理之间复杂的相互作用来塑造的。为了可靠地研究多代理行为,无监督和自我监督的学习的进步使从轨迹数据中学到了各种不同的行为表示。迄今为止,还没有一组统一的基准测试,可以在广泛的行为分析设置中进行定量和系统地比较方法。我们的目的是通过引入来自现实世界行为神经科学实验的大规模,多代理轨迹数据集来解决这一问题,该数据集涵盖了一系列行为分析任务。我们的数据集由来自通用模型生物的轨迹数据组成,其中有960万帧的小鼠数据和440万帧的飞行数据,在各种实验环境中,例如不同的菌株,相互作用的长度和光遗传学刺激。框架的子集还包括专家注销的行为标签。我们数据集的改进对应于跨多种生物的行为表示,并能够捕获常见行为分析任务的差异。
translated by 谷歌翻译