The majority of existing post-hoc explanation approaches for machine learning models produce independent per-variable feature attribution scores, ignoring a critical characteristic, such as the inter-variable relationship between features that naturally occurs in visual and textual data. In response, we develop a novel model-agnostic and permutation-based feature attribution algorithm based on the relational analysis between input variables. As a result, we are able to gain a broader insight into machine learning model decisions and data. This type of local explanation measures the effects of interrelationships between local features, which provides another critical aspect of explanations. Experimental evaluations of our framework using setups involving both image and text data modalities demonstrate its effectiveness and validity.
translated by 谷歌翻译
医学图像计算社区面临的核心挑战之一是快速有效的数据样本标签。获得细分的细粒标签以尤其要求,因为它昂贵,耗时,并且需要复杂的工具。相反,应用边界框的快速范围比细粒度的标签要少得多,但不会产生详细的结果。作为回应,我们为弱监督任务提出了一个新颖的框架,将边界盒快速转换为分割面具,而无需训练任何机器学习模型,即创建的Boxshrink。所提出的框架有两个变体 - 快速标签转换的Rapid-boxshrink,以及可靠的Boxshrink,用于更精确的标签转换。与仅使用边界盒注释作为结肠镜检查图像数据集的输入相比,在使用BoxShrink进行培训时,在几种模型中平均有4%的改善。我们为拟议的框架开源代码,并在线发布。
translated by 谷歌翻译
近年来提出了各种本地特征归因方法,后续工作提出了几种评估策略。为了评估不同归因技术的归因质量,在图像域中这些评估策略中最流行的是使用像素扰动。但是,最近的进步发现,不同的评估策略会产生归因方法的冲突排名,并且计算的昂贵。在这项工作中,我们介绍了基于像素扰动的评估策略的信息理论分析。我们的发现表明,与其实际值相比,通过删除像素的形状而不是信息泄漏的结果。使用我们的理论见解,我们提出了一个新的评估框架,称为“删除和Debias”(ROAD),该框架提供了两种贡献:首先,它减轻了混杂因素的影响,这需要在评估策略之间更高的一致性。其次,与最先进的时间相比,道路不需要计算昂贵的重新训练步骤,并节省了高达99%的计算成本。我们在https://github.com/tleemann/road_evaluation上发布源代码。
translated by 谷歌翻译
了解深度神经网络的结果是朝着更广泛接受深度学习算法的重要步骤。许多方法解决了解释人工神经网络的问题,但通常提供不同的解释。此外,不同的解释方法的超级公路可能导致互相冲突。在本文中,我们提出了一种使用受限制的Boltzmann机器(RBMS)来聚合不同解释算法的特征归属的技术,以实现对深神经网络的更可靠和坚固的解释。关于现实世界数据集的几个具有挑战性的实验表明,所提出的RBM方法优于流行的特征归因方法和基本集合技术。
translated by 谷歌翻译
异构表格数据是最常用的数据形式,对于众多关键和计算要求的应用程序至关重要。在同质数据集上,深度神经网络反复显示出卓越的性能,因此被广泛采用。但是,它们适应了推理或数据生成任务的表格数据仍然具有挑战性。为了促进该领域的进一步进展,这项工作概述了表格数据的最新深度学习方法。我们将这些方法分为三组:数据转换,专业体系结构和正则化模型。对于每个小组,我们的工作提供了主要方法的全面概述。此外,我们讨论了生成表格数据的深度学习方法,并且还提供了有关解释对表格数据的深层模型的策略的概述。因此,我们的第一个贡献是解决上述领域中的主要研究流和现有方法,同时强调相关的挑战和开放研究问题。我们的第二个贡献是在传统的机器学习方法中提供经验比较,并在五个流行的现实世界中的十种深度学习方法中,具有不同规模和不同的学习目标的经验比较。我们已将作为竞争性基准公开提供的结果表明,基于梯度增强的树合奏的算法仍然大多在监督学习任务上超过了深度学习模型,这表明对表格数据的竞争性深度学习模型的研究进度停滞不前。据我们所知,这是对表格数据深度学习方法的第一个深入概述。因此,这项工作可以成为有价值的起点,以指导对使用表格数据深入学习感兴趣的研究人员和从业人员。
translated by 谷歌翻译
Domain adaptation of GANs is a problem of fine-tuning the state-of-the-art GAN models (e.g. StyleGAN) pretrained on a large dataset to a specific domain with few samples (e.g. painting faces, sketches, etc.). While there are a great number of methods that tackle this problem in different ways there are still many important questions that remain unanswered. In this paper, we provide a systematic and in-depth analysis of the domain adaptation problem of GANs, focusing on the StyleGAN model. First, we perform a detailed exploration of the most important parts of StyleGAN that are responsible for adapting the generator to a new domain depending on the similarity between the source and target domains. In particular, we show that affine layers of StyleGAN can be sufficient for fine-tuning to similar domains. Second, inspired by these findings, we investigate StyleSpace to utilize it for domain adaptation. We show that there exist directions in the StyleSpace that can adapt StyleGAN to new domains. Further, we examine these directions and discover their many surprising properties. Finally, we leverage our analysis and findings to deliver practical improvements and applications in such standard tasks as image-to-image translation and cross-domain morphing.
translated by 谷歌翻译
Prior work has extensively studied the latent space structure of GANs for unconditional image synthesis, enabling global editing of generated images by the unsupervised discovery of interpretable latent directions. However, the discovery of latent directions for conditional GANs for semantic image synthesis (SIS) has remained unexplored. In this work, we specifically focus on addressing this gap. We propose a novel optimization method for finding spatially disentangled class-specific directions in the latent space of pretrained SIS models. We show that the latent directions found by our method can effectively control the local appearance of semantic classes, e.g., changing their internal structure, texture or color independently from each other. Visual inspection and quantitative evaluation of the discovered GAN controls on various datasets demonstrate that our method discovers a diverse set of unique and semantically meaningful latent directions for class-specific edits.
translated by 谷歌翻译
In this paper, we view a policy or plan as a transition system over a space of information states that reflect a robot's or other observer's perspective based on limited sensing, memory, computation, and actuation. Regardless of whether policies are obtained by learning algorithms, planning algorithms, or human insight, we want to know the limits of feasibility for given robot hardware and tasks. Toward the quest to find the best policies, we establish in a general setting that minimal information transition systems (ITSs) exist up to reasonable equivalence assumptions, and are unique under some general conditions. We then apply the theory to generate new insights into several problems, including optimal sensor fusion/filtering, solving basic planning tasks, and finding minimal representations for feasible policies.
translated by 谷歌翻译
决策和计划最复杂的任务之一是收集信息。当状态具有高维度,并且无法用参数分布表达其信念时,此任务就会变得更加复杂。尽管国家是高维的,但在许多问题中,其中只有一小部分可能涉及过渡状态和产生观察结果。我们利用这一事实来计算信息理论的预期奖励,共同信息(MI),在国家的较低维度子集中,以提高效率和不牺牲准确性。以前的工作中使用了类似的方法,但专门用于高斯分布,我们在这里将其扩展为一般分布。此外,我们将降低维度降低用于将新状态扩展到上一个的情况下,又不牺牲准确性。然后,我们继续开发以连续的蒙特卡洛(SMC)方式工作的MI估计器,并避免重建未来信念的表面。最后,我们展示了如何将这项工作应用于信息丰富的计划优化问题。然后在模拟主动大满贯问题的模拟中评估这项工作,其中证明了准确性和时序的提高。
translated by 谷歌翻译
与生成对抗网络(GAN)的图像和分割掩模的联合合成有望减少用像素通过像素注释收集图像数据所需的精力。但是,要学习高保真图像掩码合成,现有的GAN方法首先需要一个需要大量图像数据的预训练阶段,这限制了其在受限图像域中的利用。在这项工作中,我们迈出了一步,以减少此限制,从而引入了单次图像掩码合成的任务。我们旨在仅给出一个单个标记的示例,生成各种图像及其分割面具,并假设与以前的模型相反,则无法访问任何预训练数据。为此,我们受到单图像gan的最新体系结构发展的启发,我们介绍了OSMIS模型,该模型可以合成分割掩模,这些掩模与单次镜头中生成的图像完全一致。除了实现产生的口罩的高保真度外,OSMIS在图像合成质量和多样性中的最先进的单图像模型优于最先进的单位图。此外,尽管没有使用任何其他数据,OSMIS还是表现出令人印象深刻的能力,可以作为一击细分应用程序的有用数据增强的来源,提供了与标准数据增强技术相辅相成的性能提高。代码可从https://github.com/ boschresearch/One-shot-synthesis获得
translated by 谷歌翻译