In this paper, we propose a method for selecting the optimal footholds for legged systems. The goal of the proposed method is to find the best foothold for the swing leg on a local elevation map. We apply the Convolutional Neural Network to learn the relationship between the local elevation map and the quality of potential footholds. The proposed network evaluates the geometrical characteristics of each cell on the elevation map, checks kinematic constraints and collisions. During execution time, the controller obtains the qualitative measurement of each potential foothold from the neural model. This method allows to evaluate hundreds of potential footholds and check multiple constraints in a single step which takes 10~ms on a standard computer without GPGPU. The experiments were carried out on a quadruped robot walking over rough terrain in both simulation and real robotic platforms.
translated by 谷歌翻译
Participants in political discourse employ rhetorical strategies -- such as hedging, attributions, or denials -- to display varying degrees of belief commitments to claims proposed by themselves or others. Traditionally, political scientists have studied these epistemic phenomena through labor-intensive manual content analysis. We propose to help automate such work through epistemic stance prediction, drawn from research in computational semantics, to distinguish at the clausal level what is asserted, denied, or only ambivalently suggested by the author or other mentioned entities (belief holders). We first develop a simple RoBERTa-based model for multi-source stance predictions that outperforms more complex state-of-the-art modeling. Then we demonstrate its novel application to political science by conducting a large-scale analysis of the Mass Market Manifestos corpus of U.S. political opinion books, where we characterize trends in cited belief holders -- respected allies and opposed bogeymen -- across U.S. political ideologies.
translated by 谷歌翻译
We introduce Patch Aligned Contrastive Learning (PACL), a modified compatibility function for CLIP's contrastive loss, intending to train an alignment between the patch tokens of the vision encoder and the CLS token of the text encoder. With such an alignment, a model can identify regions of an image corresponding to a given text input, and therefore transfer seamlessly to the task of open vocabulary semantic segmentation without requiring any segmentation annotations during training. Using pre-trained CLIP encoders with PACL, we are able to set the state-of-the-art on the task of open vocabulary zero-shot segmentation on 4 different segmentation benchmarks: Pascal VOC, Pascal Context, COCO Stuff and ADE20K. Furthermore, we show that PACL is also applicable to image-level predictions and when used with a CLIP backbone, provides a general improvement in zero-shot classification accuracy compared to CLIP, across a suite of 12 image classification datasets.
translated by 谷歌翻译
We present HetNet (Multi-level \textbf{Het}erogeneous \textbf{Net}work), a highly efficient mirror detection network. Current mirror detection methods focus more on performance than efficiency, limiting the real-time applications (such as drones). Their lack of efficiency is aroused by the common design of adopting homogeneous modules at different levels, which ignores the difference between different levels of features. In contrast, HetNet detects potential mirror regions initially through low-level understandings (\textit{e.g.}, intensity contrasts) and then combines with high-level understandings (contextual discontinuity for instance) to finalize the predictions. To perform accurate yet efficient mirror detection, HetNet follows an effective architecture that obtains specific information at different stages to detect mirrors. We further propose a multi-orientation intensity-based contrasted module (MIC) and a reflection semantic logical module (RSL), equipped on HetNet, to predict potential mirror regions by low-level understandings and analyze semantic logic in scenarios by high-level understandings, respectively. Compared to the state-of-the-art method, HetNet runs 664$\%$ faster and draws an average performance gain of 8.9$\%$ on MAE, 3.1$\%$ on IoU, and 2.0$\%$ on F-measure on two mirror detection benchmarks.
translated by 谷歌翻译
在图像分类中,在检测分布(OOD)数据时发生了许多发展。但是,大多数OOD检测方法是在一组标准数据集上评估的,该数据集与培训数据任意不同。没有明确的定义``好的''ood数据集。此外,最先进的OOD检测方法已经在这些标准基准上取得了几乎完美的结果。在本文中,我们定义了2类OOD数据使用与分布(ID)数据的感知/视觉和语义相似性的微妙概念。我们将附近的OOD样本定义为感知上相似但语义上与ID样本的不同,并将样本转移为视觉上不同但在语义上与ID相似的点数据。然后,我们提出了一个基于GAN的框架,用于从这两个类别中生成OOD样品,给定一个ID数据集。通过有关MNIST,CIFAR-10/100和Imagenet的广泛实验,我们表明A)在常规基准上表现出色的ART OOD检测方法对我们提出的基准测试的稳健性明显较小。 N基准测试,反之亦然,因此表明甚至可能不需要单独的OOD集来可靠地评估OOD检测中的性能。
translated by 谷歌翻译
通用数据模型解决了标准化电子健康记录(EHR)数据的许多挑战,但无法将其集成深度表型所需的资源。开放的生物学和生物医学本体论(OBO)铸造本体论提供了可用于生物学知识的语义计算表示,并能够整合多种生物医学数据。但是,将EHR数据映射到OBO Foundry本体论需要大量的手动策展和域专业知识。我们介绍了一个框架,用于将观察性医学成果合作伙伴关系(OMOP)标准词汇介绍给OBO铸造本体。使用此框架,我们制作了92,367条条件,8,615种药物成分和10,673个测量结果的映射。域专家验证了映射准确性,并且在24家医院进行检查时,映射覆盖了99%的条件和药物成分和68%的测量结果。最后,我们证明OMOP2OBO映射可以帮助系统地识别可能受益于基因检测的未诊断罕见病患者。
translated by 谷歌翻译
基于决策树(DT)的分类和回归思想,最近提议在总体分类和回归任务中提供更高的性能。以更高的计算复杂性为代价,达到了其性能的改进。在这项工作中,我们研究了两种加速SLM的方法。首先,我们采用粒子群优化(PSO)算法来加快对当前尺寸的线性组合表示的判别尺寸的搜索。线性组合中最佳权重的搜索在计算上很重。它是通过原始SLM中的概率搜索来完成的。 PSO的SLM加速需要减少10-20倍的迭代。其次,我们利用SLM实施中的并行处理。实验结果表明,加速的SLM方法在训练时间中达到577的速度系数,同时保持原始SLM的可比分类/回归性能。
translated by 谷歌翻译
本文研究了一个开放的研究问题,即生成文本图像对,以改善细粒度对文本跨模式检索任务的训练,并通过发现stylegan2模型的隐藏语义信息,为配对数据增强的新颖框架提出了一个新颖的框架。 。具体来说,我们首先在给定数据集上训练stylegan2模型。然后,我们将真实图像投影回stylegan2的潜在空间,以获取潜在的代码。为了使生成的图像可操作,我们进一步引入了一个潜在的空间对齐模块,以了解StyleGAN2潜在代码和相应的文本字幕功能之间的对齐。当我们进行在线配对数据增强时,我们首先通过随机代码替换生成增强文本,然后将增强文本传递到潜在的空间对齐模块中以输出潜在代码,最终将其馈送到stylegan2以生成增强图像。我们评估了增强数据方法对两个公共跨模式检索数据集的功效,其中有希望的实验结果表明,可以将增强的文本图像对数据与原始数据一起训练,以增强图像到文本交叉 - 模态检索性能。
translated by 谷歌翻译
在本文中,我们调查了一项开放的研究任务,该任务是从单个2D GAN产生人体面部且没有3D监督的3D卡通面部形状,在那里我们还可以操纵3D形状的面部表情。为此,我们发现了Stylegan潜在空间的语义含义,因此我们能够通过控制潜在代码来产生各种表达式,姿势和照明的面部图像。具体而言,我们首先对卡通数据集中预验证的Stylegan脸部模型进行了修复。通过将相同的潜在代码喂入面部和卡通生成模型,我们的目标是实现从2D人脸图像到卡通风格的化身的翻译。然后,我们发现了甘恩潜在空间的语义方向,以试图在保留原始身份的同时改变面部表情。由于我们没有任何针对卡通脸的3D注释,因此我们操纵潜在代码以生成具有不同姿势和照明的图像,以便我们可以重建3D卡通脸部形状。我们在定性和定量上验证了方法在三个卡通数据集上的疗效。
translated by 谷歌翻译
现有的伪装对象检测(COD)方法在很大程度上依赖于具有像素注释的大规模数据集。但是,由于边界模棱两可,注释伪装物体像素 - 智能(每图像需要约60分钟),这是非常耗时的和劳动密集型的。在本文中,我们使用涂鸦注释作为监督提出了第一个弱监督的伪装对象检测(COD)方法。为了实现这一目标,我们首先构建了一个带有4,040张图像和相应涂鸦注释的基于涂鸦的伪装对象数据集。值得注意的是,注释我们数据集中使用的涂鸦每图像仅需约10秒钟,这比每像素注释快360倍。但是,直接使用涂鸦注释进行监督的网络将无法本地化伪装对象的边界,并且往往会有不一致的预测,因为涂鸦注释仅描述了没有细节的对象的主要结构。为了解决这个问题,我们提出了一个由两个部分组成的新型一致性损失:可靠的跨视图损失,以在不同图像上获得可靠的一致性,以及在单个预测图内保持一致性的软内部视图损失。此外,我们观察到,人类使用语义信息来段区域接近伪装物体的边界。因此,我们设计了一个特征引导的损失,其中包括直接从图像中提取的视觉特征和模型捕获的语义显着特征。此外,我们提出了一个新颖的网络,该网络通过对结构信息和语义关系进行涂鸦学习来检测伪装的对象。实验结果表明,我们的模型在三个COD基准上的表现优于相关的最新方法,MAE的平均提高为11.0%,S量表为3.2%,E-Measure 2.5%,加权F-的4.4%。措施。
translated by 谷歌翻译