为了在医学成像研究中保持标准,图像应具有必要的图像质量,以进行潜在的诊断使用。尽管基于CNN的方法用于评估图像质量,但仍可以从准确性方面提高其性能。在这项工作中,我们通过使用SWIN Transformer来解决此问题,这改善了导致医疗图像质量降解的质量质量差分类性能。我们在胸部X射线(Object-CXR)和心脏MRI上的左心室流出路分类问题(LVOT)上测试了胸部X射线(Object-CXR)和左心室流出路分类问题的方法。虽然我们在Object-CXR和LVOT数据集中获得了87.1%和95.48%的分类精度,但我们的实验结果表明,SWIN Transformer的使用可以改善对象CXR分类性能,同时获得LVOT数据集的可比性能。据我们所知,我们的研究是医学图像质量评估的第一个Vision Transformer应用程序。
translated by 谷歌翻译
Ranking intuitionistic fuzzy sets with distance based ranking methods requires to calculate the distance between intuitionistic fuzzy set and a reference point which is known to have either maximum (positive ideal solution) or minimum (negative ideal solution) value. These group of approaches assume that as the distance of an intuitionistic fuzzy set to the reference point is decreases, the similarity of intuitionistic fuzzy set with that point increases. This is a misconception because an intuitionistic fuzzy set which has the shortest distance to positive ideal solution does not have to be the furthest from negative ideal solution for all circumstances when the distance function is nonlinear. This paper gives a mathematical proof of why this assumption is not valid for any of the non-linear distance functions and suggests a hypervolume based ranking approach as an alternative to distance based ranking. In addition, the suggested ranking approach is extended as a new multicriteria decision making method, HyperVolume based ASsessment (HVAS). HVAS is applied for multicriteria assessment of Turkey's energy alternatives. Results are compared with three well known distance based multicriteria decision making methods (TOPSIS, VIKOR, and CODAS).
translated by 谷歌翻译
We investigate ensemble methods for prediction in an online setting. Unlike all the literature in ensembling, for the first time, we introduce a new approach using a meta learner that effectively combines the base model predictions via using a superset of the features that is the union of the base models' feature vectors instead of the predictions themselves. Here, our model does not use the predictions of the base models as inputs to a machine learning algorithm, but choose the best possible combination at each time step based on the state of the problem. We explore three different constraint spaces for the ensembling of the base learners that linearly combines the base predictions, which are convex combinations where the components of the ensembling vector are all nonnegative and sum up to 1; affine combinations where the weight vector components are required to sum up to 1; and the unconstrained combinations where the components are free to take any real value. The constraints are both theoretically analyzed under known statistics and integrated into the learning procedure of the meta learner as a part of the optimization in an automated manner. To show the practical efficiency of the proposed method, we employ a gradient-boosted decision tree and a multi-layer perceptron separately as the meta learners. Our framework is generic so that one can use other machine learning architectures as the ensembler as long as they allow for a custom differentiable loss for minimization. We demonstrate the learning behavior of our algorithm on synthetic data and the significant performance improvements over the conventional methods over various real life datasets, extensively used in the well-known data competitions. Furthermore, we openly share the source code of the proposed method to facilitate further research and comparison.
translated by 谷歌翻译
The goal of this work is to localize sound sources in visual scenes with a self-supervised approach. Contrastive learning in the context of sound source localization leverages the natural correspondence between audio and visual signals where the audio-visual pairs from the same source are assumed as positive, while randomly selected pairs are negatives. However, this approach brings in noisy correspondences; for example, positive audio and visual pair signals that may be unrelated to each other, or negative pairs that may contain semantically similar samples to the positive one. Our key contribution in this work is to show that using a less strict decision boundary in contrastive learning can alleviate the effect of noisy correspondences in sound source localization. We propose a simple yet effective approach by slightly modifying the contrastive loss with a negative margin. Extensive experimental results show that our approach gives on-par or better performance than the state-of-the-art methods. Furthermore, we demonstrate that the introduction of a negative margin to existing methods results in a consistent improvement in performance.
translated by 谷歌翻译
由于钻孔对准的困难以及任务的固有不稳定性,在手动完成时,在弯曲的表面上钻一个孔很容易失败,可能会对工人造成伤害和疲劳。另一方面,在实际制造环境中充分自动化此类任务可能是不切实际的,因为到达装配线的零件可以具有各种复杂形状,在这些零件上不容易访问钻头位置,从而使自动化路径计划变得困难。在这项工作中,开发并部署了一个具有6个自由度的自适应入学控制器,并部署在Kuka LBR IIWA 7配件上,使操作员能够用一只手舒适地在机器人上安装在机器人上的钻头,并在弯曲的表面上开放孔,并在弯曲的表面上开放孔。通过AR界面提供的玉米饼和视觉指导的触觉指导。接收阻尼的实时适应性在自由空间中驱动机器人时,可以在确保钻孔过程中稳定时提供更高的透明度。用户将钻头足够靠近钻头目标并大致与所需的钻探角度对齐后,触觉指导模块首先对对齐进行微调,然后将用户运动仅限于钻孔轴,然后操作员仅将钻头推动钻头以最小的努力进入工件。进行了两组实验,以定量地研究触觉指导模块的潜在好处(实验I),以及根据参与者的主观意见(实验II),提出的用于实际制造环境的PHRI系统的实际价值。
translated by 谷歌翻译
展开的神经网络最近实现了最先进的MRI重建。这些网络通过在基于物理的一致性和基于神经网络的正则化之间交替来展开迭代优化算法。但是,它们需要大型神经网络的几次迭代来处理高维成像任务,例如3D MRI。这限制了基于反向传播的传统训练算法,这是由于较大的记忆力和计算梯度和存储中间激活的计算要求。为了应对这一挑战,我们提出了加速MRI(GLEAM)重建的贪婪学习,这是一种高维成像设置的有效培训策略。 GLEAM将端到端网络拆分为脱钩的网络模块。每个模块都以贪婪的方式优化,并通过脱钩的梯度更新,从而减少了训练过程中的内存足迹。我们表明,可以在多个图形处理单元(GPU)上并行执行解耦梯度更新,以进一步减少训练时间。我们介绍了2D和3D数据集的实验,包括多线圈膝,大脑和动态心脏Cine MRI。我们观察到:i)闪闪发光的概括以及最先进的记忆效率基线,例如具有相同内存足迹的梯度检查点和可逆网络,但训练速度更快1.3倍; ii)对于相同的内存足迹,闪光在2D中产生1.1dB PSNR的增益,而3D在端到端基线中产生1.8 dB。
translated by 谷歌翻译
我们开发了快速算法和可靠软件,以凸出具有Relu激活功能的两层神经网络的凸优化。我们的工作利用了标准的重量罚款训练问题作为一组组-YELL_1 $调查的数据本地模型的凸重新印度,其中局部由多面体锥体约束强制执行。在零规范化的特殊情况下,我们表明此问题完全等同于凸“ Gated Relu”网络的不受约束的优化。对于非零正则化的问题,我们表明凸面式relu模型获得了RELU训练问题的数据依赖性近似范围。为了优化凸的重新制定,我们开发了一种加速的近端梯度方法和实用的增强拉格朗日求解器。我们表明,这些方法比针对非凸问题(例如SGD)和超越商业内部点求解器的标准训练启发式方法要快。在实验上,我们验证了我们的理论结果,探索组-ELL_1 $正则化路径,并对神经网络进行比例凸的优化,以在MNIST和CIFAR-10上进行图像分类。
translated by 谷歌翻译
安全聚合是一个流行的保留联合学习中的流行协议,它允许模型聚合,而不会在清除中显示各个模型。另一方面,传统的安全聚合协议产生了显着的通信开销,这可能成为现实世界带宽限制应用中的主要瓶颈。在解决这一挑战方面,在这项工作中,我们提出了一种用于安全聚合的轻量级渐变稀疏框架,其中服务器从大量用户学习Sparsified本地模型更新的聚合,但不学习各个参数。我们的理论分析表明,所提出的框架可以显着降低安全聚合的通信开销,同时确保可比计算复杂性。我们进一步确定了由于稀疏因疏脂而在隐私和沟通效率之间的权衡。我们的实验表明,我们的框架在与传统安全聚合基准相比时,我们的框架将延长到7.8倍降低了高达7.8倍,同时加速了墙上时钟训练时间1.13x。
translated by 谷歌翻译
深语模型在NLP域中取得了显着的成功。培养深层语言模型的标准方法是从大型未标记的语料库中雇用无监督的学习。但是,这种大型公司仅适用于广泛采用和高资源语言和域名。本研究提出了第一款深语型号DPRK-BERT为朝鲜语言。我们通过编制朝鲜语言的第一个未标记的语料库和微调预先存在的ROK语言模型来实现这一目标。我们将所提出的模型与现有方法进行比较,并显示两个DPRK数据集的显着改进。我们还提供了这种模型的交叉语言版本,其在两种韩语语言中产生了更好的泛化。最后,我们提供与朝鲜语言相关的各种NLP工具,这些工具将培养未来的研究。
translated by 谷歌翻译
在本文中,我们提出了一种基于对比学习的完全监督的预培训方案,特别针对密集的分类任务。所提出的上下文 - 自我对比损失(CSCL)了解嵌入空间,通过在训练样本中的每个位置与其本地上下文之间使用相似性度量来弹出语义边界。对于从卫星图像时间序列(坐)的作物类型语义分割我们在宗地边界中发现性能是一个关键的瓶颈,并解释CSCL如何解决该问题的潜在原因,从而提高本任务中的最先进的性能。此外,我们使用来自Sentinel-2(S2)卫星任务的图像,我们编写了我们的知识,坐在裁剪类型和包裹身份密集地注释的数据集,我们将与数据生成管道一起公开使用。使用我们发现CSCL的数据,即使具有最小的预训练,以改善所有相应的基线,并且在超级分辨率下提出语义分割的过程,以获得更粒度的茶几。下载数据的代码和说明可以在https://github.com/michaeltrs/deepsatmodels中找到。
translated by 谷歌翻译