Medical image segmentation is an actively studied task in medical imaging, where the precision of the annotations is of utter importance towards accurate diagnosis and treatment. In recent years, the task has been approached with various deep learning systems, among the most popular models being U-Net. In this work, we propose a novel strategy to generate ensembles of different architectures for medical image segmentation, by leveraging the diversity (decorrelation) of the models forming the ensemble. More specifically, we utilize the Dice score among model pairs to estimate the correlation between the outputs of the two models forming each pair. To promote diversity, we select models with low Dice scores among each other. We carry out gastro-intestinal tract image segmentation experiments to compare our diversity-promoting ensemble (DiPE) with another strategy to create ensembles based on selecting the top scoring U-Net models. Our empirical results show that DiPE surpasses both individual models as well as the ensemble creation strategy based on selecting the top scoring models.
translated by 谷歌翻译
表面分级是在施工现场管道中的一项重要任务,这是平衡含有预倾角沙桩的不平衡区域的过程。这种劳动密集型过程通常是由任何建筑工地的关键机械工具推土机进行的。当前的自动化表面分级的尝试实现了完美的定位。但是,在实际情况下,由于代理人的感知不完善,因此该假设失败了,从而导致性能降解。在这项工作中,我们解决了不确定性下自动分级的问题。首先,我们实施模拟和缩放现实世界原型环境,以在此环境中快速策略探索和评估。其次,我们将问题形式化为部分可观察到的马尔可夫决策过程,并培训能够处理此类不确定性的代理商。我们通过严格的实验表明,经过完美本地化训练的代理人在出现本地化不确定性时会遭受降低的性能。但是,使用我们的方法培训的代理商将制定更强大的政策来解决此类错误,从而表现出更好的评分性能。
translated by 谷歌翻译
混乱场景中的物体操纵是机器人技术中的一个困难和重要问题。为了有效地操纵物体,重要的是要了解它们的周围环境,尤其是在将一个物体堆叠在另一个物体的情况下,以防止有效抓握。我们在这里提出Duqim-Net,这是一种在堆叠对象的设置中进行对象操作的决策方法。在DUQIM-NET中,使用Adj-Net评估层次堆叠关系,该模型通过添加邻接头来利用现有的变压器编码器编码器对象检测器。该头部的输出概率地渗透了场景中对象的基础层次结构。我们利用DUQIM-NET中的邻接矩阵的属性来执行决策并协助对象抓任务。我们的实验结果表明,ADJ-NET超过了视觉操作关系数据集(VMRD)的对象关系推断的最新技术,并且DUQIM-NET在bin清除任务中的表现优于可比的方法。
translated by 谷歌翻译
在这项工作中,我们旨在解决自动分级问题,在这种情况下,必须将推土机弄平不平衡的区域。此外,我们探索了弥合模拟环境和实际场景之间差距的方法。我们设计了一个现实的物理模拟,也是模仿真实推土机动力学和感官信息的缩放的真实原型环境。我们建立了启发式方法和学习策略,以解决问题。通过广泛的实验,我们表明,尽管启发式方法能够在清洁且无噪音的模拟环境中解决该问题,但在面对现实世界情景时,它们在灾难性的环境中失败。由于启发式方法能够在模拟环境中成功解决任务,因此我们表明它们可以被利用来指导学习代理,该学习代理可以在模拟和缩放原型环境中概括和解决任务。
translated by 谷歌翻译
在这项工作中,我们建立了对砂桩镶嵌的不均匀区域的解说中的自治控制的启发式和学习策略。我们将问题正式化为马尔可夫决策过程,设计了一个演示了代理环境交互的模拟,最后将我们的模拟器与真正的Dozer原型进行了比较。我们使用钢筋学习,行为克隆和对比学习的方法来培训混合政策。我们的培训代理AGPNET达到人力级性能,优于自主分级任务的当前最先进的机器学习方法。此外,我们的代理能够从随机情景中推广到看不见的世界问题。
translated by 谷歌翻译
Kendall转换是将有序功能转换为单个值之间的成对订单关系的向量。这样,它保留了观察的排名,并以分类形式表示它。这种转化允许需要严格分类输入的方法的概括,尤其是在离散方式发生问题时在少量观察的极限中。特别地,可以直接应用信息理论方法,而不依赖于差分熵或任何附加参数。此外,通过将信息过滤到排名中的信息,Kendall转换以合理的成本导致更好的稳健性,其丢弃了复杂的相互作用,这不太可能被正确估计。在双变量分析中,肯德尔转型可以与流行的非参数方法有关,呈现方法的健全性。本文还展示了其在多变量问题中的效率,并提供了对真实数据的示例分析。
translated by 谷歌翻译
Catastrophic forgetting occurs when a neural network loses the information learned in a previous task after training on subsequent tasks. This problem remains a hurdle for artificial intelligence systems with sequential learning capabilities. In this paper, we propose a task-based hard attention mechanism that preserves previous tasks' information without affecting the current task's learning. A hard attention mask is learned concurrently to every task, through stochastic gradient descent, and previous masks are exploited to condition such learning. We show that the proposed mechanism is effective for reducing catastrophic forgetting, cutting current rates by 45 to 80%. We also show that it is robust to different hyperparameter choices, and that it offers a number of monitoring capabilities. The approach features the possibility to control both the stability and compactness of the learned knowledge, which we believe makes it also attractive for online learning or network compression applications.
translated by 谷歌翻译