Satellite image change detection aims at finding occurrences of targeted changes in a given scene taken at different instants. This task is highly challenging due to the acquisition conditions and also to the subjectivity of changes. In this paper, we investigate satellite image change detection using active learning. Our method is interactive and relies on a question and answer model which asks the oracle (user) questions about the most informative display (dubbed as virtual exemplars), and according to the user's responses, updates change detections. The main contribution of our method consists in a novel adversarial model that allows frugally probing the oracle with only the most representative, diverse and uncertain virtual exemplars. The latter are learned to challenge the most the trained change decision criteria which ultimately leads to a better re-estimate of these criteria in the following iterations of active learning. Conducted experiments show the out-performance of our proposed adversarial display model against other display strategies as well as the related work.
translated by 谷歌翻译
In this paper, we design lightweight graph convolutional networks (GCNs) using a particular class of regularizers, dubbed as phase-field models (PFMs). PFMs exhibit a bi-phase behavior using a particular ultra-local term that allows training both the topology and the weight parameters of GCNs as a part of a single "end-to-end" optimization problem. Our proposed solution also relies on a reparametrization that pushes the mask of the topology towards binary values leading to effective topology selection and high generalization while implementing any targeted pruning rate. Both masks and weights share the same set of latent variables and this further enhances the generalization power of the resulting lightweight GCNs. Extensive experiments conducted on the challenging task of skeleton-based recognition show the outperformance of PFMs against other staple regularizers as well as related lightweight design methods.
translated by 谷歌翻译
Most of the existing learning models, particularly deep neural networks, are reliant on large datasets whose hand-labeling is expensive and time demanding. A current trend is to make the learning of these models frugal and less dependent on large collections of labeled data. Among the existing solutions, deep active learning is currently witnessing a major interest and its purpose is to train deep networks using as few labeled samples as possible. However, the success of active learning is highly dependent on how critical are these samples when training models. In this paper, we devise a novel active learning approach for label-efficient training. The proposed method is iterative and aims at minimizing a constrained objective function that mixes diversity, representativity and uncertainty criteria. The proposed approach is probabilistic and unifies all these criteria in a single objective function whose solution models the probability of relevance of samples (i.e., how critical) when learning a decision function. We also introduce a novel weighting mechanism based on reinforcement learning, which adaptively balances these criteria at each training iteration, using a particular stateless Q-learning model. Extensive experiments conducted on staple image classification data, including Object-DOTA, show the effectiveness of our proposed model w.r.t. several baselines including random, uncertainty and flat as well as other work.
translated by 谷歌翻译
大型和性能的神经网络通常过度参数化,并且由于修剪而可以大大降低大小和复杂性。修剪是一组方法,它试图消除网络中的冗余或不必要的权重或权重。这些技术允许创建轻型网络,这对于嵌入式或移动应用程序特别重要。在本文中,我们设计了一种替代修剪方法,允许从较大未训练的方法中提取有效的子网。我们的方法是随机的,并通过探索使用Gumbel SoftMax采样的不同拓扑来提取子网。后者还用于训练概率分布,以衡量样品中权重的相关性。使用高效的重新恢复机制进一步增强了最终的子网,从而减少训练时间并提高性能。在CIFAR上进行的广泛实验表明,针对相关工作,我们的子网络提取方法的表现要优于表现。
translated by 谷歌翻译
学习图形卷积网络(GCNS)是一种新兴领域,其旨在将卷积操作概括为任意非常规域。特别地,与光谱域相比,在空间域操作的GCNS显示出优异的性能,但它们的成功高度依赖于如何定义输入图的拓扑。在本文中,我们向图表卷积网络介绍了一个新颖的框架,了解图形的拓扑属性。我们的方法的设计原理基于约束目标函数的优化,该函数不仅在GCNS中的常用卷积参数中学习,而且是传达这些图中最相关的拓扑关系的转换基础。基于骨架的动作识别的具有挑战性任务进行的实验表明,与手工图形设计以及相关工作相比,所提出的方法的优越性。
translated by 谷歌翻译
深度神经网络(DNN)最近在计算机视觉和几个相关领域取得了巨大成功。尽管如此,目前的神经结构仍然遭受灾难性干扰(A.K.A.忘记),这阻碍了DNN不断学习。虽然已经提出了几种最先进的方法来缓解遗忘,但这些现有解决方案是高度僵化的(正则化)或时间/内存要求(作为重播)。在文献中提出了一种基于动态网络的中等方法,并在文献中提出了在任务记忆和计算足迹之间提供合理的平衡。在本文中,我们基于一种基于新颖的无遗忘神经块(FFNB)来设计用于持续学习的动态网络架构。使用新的程序实现新任务的FFNB功能,该程序可以通过在前一个任务的空空间中约束底层参数,而训练分类器参数等同于Fisher判别分析。后者提供了一种有效的增量过程,这也是贝叶斯视角的最佳。使用增量的“端到端”微调进一步增强了训练有素的功能和分类器。在不同具有挑战性的分类问题上进行的大量实验,表明了该方法的高效性。
translated by 谷歌翻译
光谱图卷积网络(GCNS)是特别的深层模型,其目的在于将神经网络扩展到任意的不规则域。这些网络的原理包括使用Laplacians的特征分解突出图信号,然后在将所产生的滤波信号返回到输入图域之前在光谱域中实现滤波。然而,这些操作的成功高度依赖于主要手工制作的二手拉普拉斯人的相关性,这使得GCN明显次优。在本文中,我们介绍了一种新颖的光谱GCN,不仅可以仅限于通常的卷积参数,而且是拉普拉斯运营商。后者设计了“端到端”作为递归Chebyshev分解的一部分,其特殊性地传送了学习表示的差异和非差异性质 - 随着顺序和辨别力的增加 - 没有过分统计化训练有素的GCN。对基于骨架的动作识别的具有挑战性的任务进行了广泛的实验,展示了我们提出的拉普拉斯设计的泛化能力和表现优惠。不同的基线(建造在手工制作和其他学习的拉普拉斯人)以及相关工作。
translated by 谷歌翻译
图表卷积网络(GCNS)旨在扩展深度学习,以任意不规则域,即图表。它们的成功高度依赖于如何定义输入图的拓扑结构,并且大多数现有的GCN架构依赖于预定义或手工制作的图形结构。在本文中,我们介绍了一种新的方法,该方法将输入图的拓扑(或连接)作为GCN设计的一部分。我们方法的主要贡献驻留在建立正交的连接基础上,以便在实现卷积之前通过其邻居优化节点。我们的方法还考虑了一个时剧性标准,它作为符合规范器,使学习基础和潜在的GCNS轻质,同时仍然非常有效。对基于骨架的手势识别的挑战性任务进行了实验,展示了学习GCNS W.R.T的高效率。相关工作。
translated by 谷歌翻译
我们为半监督学习设置提供了一种新的数据增强技术,该技术强调从功能空间最具挑战性的地区学习。从完全监督的参考模型开始,我们首先确定较低的置信度预测。然后,这些样品用于训练变异自动编码器(VAE),该变量可以生成具有相似分布的无限额外图像。最后,使用最初标记的数据和合成生成的标记和未标记的数据,我们以半监视的方式重新训练了一个新模型。我们对两个基准RGB数据集进行实验:CIFAR-100和STL-10,并表明所提出的方案在准确性和鲁棒性方面提高了分类性能,同时就现有的完全监督的方法而产生可比或优越的结果。
translated by 谷歌翻译
学习在未知环境中安全导航是监视和救援操作中使用的自动无人机的重要任务。近年来,已经提出了许多基于学习的同时定位和映射(SLAM)系统,这些系统依靠深神经网络(DNN)(DNNS)提出了用于传统功能描述符表现不佳的应用。但是,这种基于学习的SLAM系统依靠DNN功能编码在典型的深度学习环境中训练有素的离线训练。这使得它们不太适合在训练中未见的环境中部署的无人机,在训练中,持续适应至关重要。在本文中,我们提出了一种新的方法,可以通过调节低复杂性词典学习和稀疏编码(DLSC)管道,并使用新提出的二次贝叶斯惊喜(QBS)因素调节,以学习在未知环境中即时猛烈抨击。我们通过在充满挑战的仓库场景中通过无人机收集的数据来实验验证我们的方法,在这种情况下,大量模棱两可的场景使视觉上的歧义很难。
translated by 谷歌翻译