Since the mid-10s, the era of Deep Learning (DL) has continued to this day, bringing forth new superlatives and innovations each year. Nevertheless, the speed with which these innovations translate into real applications lags behind this fast pace. Safety-critical applications, in particular, underlie strict regulatory and ethical requirements which need to be taken care of and are still active areas of debate. eXplainable AI (XAI) and privacy-preserving machine learning (PPML) are both crucial research fields, aiming at mitigating some of the drawbacks of prevailing data-hungry black-box models in DL. Despite brisk research activity in the respective fields, no attention has yet been paid to their interaction. This work is the first to investigate the impact of private learning techniques on generated explanations for DL-based models. In an extensive experimental analysis covering various image and time series datasets from multiple domains, as well as varying privacy techniques, XAI methods, and model architectures, the effects of private training on generated explanations are studied. The findings suggest non-negligible changes in explanations through the introduction of privacy. Apart from reporting individual effects of PPML on XAI, the paper gives clear recommendations for the choice of techniques in real applications. By unveiling the interdependencies of these pivotal technologies, this work is a first step towards overcoming the remaining hurdles for practically applicable AI in safety-critical domains.
translated by 谷歌翻译
随着深度学习(DL)的出现,超分辨率(SR)也已成为一个蓬勃发展的研究领域。然而,尽管结果有希望,但该领域仍然面临需要进一步研究的挑战,例如,允许灵活地采样,更有效的损失功能和更好的评估指标。我们根据最近的进步来回顾SR的域,并检查最新模型,例如扩散(DDPM)和基于变压器的SR模型。我们对SR中使用的当代策略进行了批判性讨论,并确定了有前途但未开发的研究方向。我们通过纳入该领域的最新发展,例如不确定性驱动的损失,小波网络,神经体系结构搜索,新颖的归一化方法和最新评估技术来补充先前的调查。我们还为整章中的模型和方法提供了几种可视化,以促进对该领域趋势的全球理解。最终,这篇综述旨在帮助研究人员推动DL应用于SR的界限。
translated by 谷歌翻译
人们普遍认为,人类视觉系统偏向于识别形状而不是纹理。这一假设导致了越来越多的工作,旨在使深层模型的决策过程与人类视野的基本特性保持一致。人们对形状特征的依赖主要预计会改善协变量转移下这些模型的鲁棒性。在本文中,我们重新审视了形状偏置对皮肤病变图像分类的重要性。我们的分析表明,不同的皮肤病变数据集对单个图像特征表现出不同的偏见。有趣的是,尽管深层提取器倾向于学习对皮肤病变分类的纠缠特征,但仍然可以从该纠缠的表示形式中解码单个特征。这表明这些功能仍在模型的学习嵌入空间中表示,但不用于分类。此外,不同数据集的光谱分析表明,与常见的视觉识别相反,皮肤皮肤病变分类本质上依赖于超出形状偏置的复杂特征组合。自然的结果,在某些情况下,摆脱了形状偏见模型的普遍欲望甚至可以改善皮肤病变分类器。
translated by 谷歌翻译
两阶段探测器在物体检测和行人检测中是最新的。但是,当前的两个阶段探测器效率低下,因为它们在多个步骤中进行边界回归,即在区域提案网络和边界框头中进行回归。此外,基于锚的区域提案网络在计算上的训练价格很高。我们提出了F2DNET,这是一种新型的两阶段检测体系结构,通过使用我们的焦点检测网络和边界框以我们的快速抑制头替换区域建议网络,从而消除了当前两阶段检测器的冗余。我们在顶级行人检测数据集上进行基准F2DNET,将其与现有的最新检测器进行彻底比较,并进行交叉数据集评估,以测试我们模型对未见数据的普遍性。我们的F2DNET在城市人员,加州理工学院行人和欧元城市人数据集中分别获得8.7 \%,2.2 \%和6.1 \%MR-2,分别在单个数据集上进行培训并达到20.4 \%\%\%和26.2 \%MR-2。使用渐进式微调时,加州理工学院行人和城市人员数据集的重型闭塞设置。此外,与当前的最新时间相比,F2DNET的推理时间明显较小。代码和训练有素的模型将在https://github.com/abdulhannankhan/f2dnet上找到。
translated by 谷歌翻译
在临床工作流程中成功部署AI的计算机辅助诊断(CAD)系统的一个主要障碍是它们缺乏透明决策。虽然常用可解释的AI方法提供了一些对不透明算法的洞察力,但除了高度训练的专家外,这种解释通常是复杂的,而不是易于理解的。关于皮肤病图像的皮肤病病变恶性的决定的解释需要特别清晰,因为潜在的医疗问题定义本身是模棱两可的。这项工作提出了exaid(可解释的ai用于皮肤科),是生物医学图像分析的新框架,提供了由易于理解的文本解释组成的多模态概念的解释,该概念由可视地图证明预测的视觉映射。 Exap依赖于概念激活向量,将人类概念映射到潜在空间中的任意深度学习模型学习的人,以及概念本地化地图,以突出输入空间中的概念。然后,这种相关概念的识别将用于构建由概念 - 明智地点信息补充的细粒度文本解释,以提供全面和相干的多模态解释。所有信息都在诊断界面中全面呈现,用于临床常规。教育模式为数据和模型探索提供数据集级别解释统计和工具,以帮助医学研究和教育。通过严谨的exaid定量和定性评估,即使在错误的预测情况下,我们展示了CAD辅助情景的多模态解释的效用。我们认为突然将为皮肤科医生提供一种有效的筛查工具,他们都理解和信任。此外,它将是其他生物医学成像领域的类似应用的基础。
translated by 谷歌翻译
数据到文本生成系统旨在基于输入数据生成文本描述(通常以表格形式表示)。典型系统使用巨大的训练样本来学习表和文本之间的对应关系。然而,大型训练套装昂贵,可以获得这些方法在现实世界方案中的适用性。在这项工作中,我们专注于几次数据到文本生成。我们观察到,虽然微调预训练的语言模型可能会产生合理的句子,但它们在几次拍摄设置中遭受了低语义覆盖问题。换句话说,生成的文本中的重要输入时隙往往丢失。为此,我们提出了一种搜索和学习方法,可以利用预训练的语言模型,而是插入丢失的插槽以提高语义覆盖。我们根据搜索结果进一步微调我们的系统,以平滑搜索噪声,在很大程度上产生更好的质量文本并提高推理效率。实验表明,我们的模型在E2E和Wikibio数据集上实现了高性能。特别是,我们在E2E上覆盖了98.35%的输入槽,很大程度上减轻了低覆盖问题。
translated by 谷歌翻译
随着机器学习的出现,在医疗保健和能源等关键基础设施的应用中,隐私是利益相关者的思想中越来越令人担忧。它是衡量的,确保模型和数据都不能用于提取攻击者对个人使用的敏感信息或通过利用关键基础设施来伤害整个社会。由于缺乏关于透明度和隐私约束的信任,机器学习在这些域中的适用性主要是有限的。各种安全关键用例(主要依赖于时间序列数据)目前在隐私相关的考虑因素方面受到了代表性。通过评估有关其在时间序列数据的适用性的若干隐私保留方法,我们验证了加密对深度学习的影响,差异隐私的强大数据集依赖性以及联合方法的广泛适用性。
translated by 谷歌翻译
通过Navier-Stokes方程的数值解决方案的计算流体动力学(CFD)仿真是从工程设计到气候建模的广泛应用中的重要工具。然而,CFD代码所需的计算成本和内存需求对于实际兴趣的流动可能变得非常高,例如在空气动力学形状优化中。该费用与流体流动控制方程的复杂性有关,其包括具有困难的解决方案的非线性部分衍生术语,导致长的计算时间和限制在迭代设计过程中可以测试的假设的数量。因此,我们提出了DeepCFD:基于卷积神经网络(CNN)的模型,其有效地近似于均匀稳态流动问题的解决方案。所提出的模型能够直接从使用最先进的CFD代码生成的地面真实数据的速度和压力场的完整解决方案的完整解决方案。使用DeepCFD,与标准CFD方法以低误差率的成本相比,我们发现高达3个数量级的加速。
translated by 谷歌翻译
In this paper, we address the challenge of land use and land cover classification using Sentinel-2 satellite images. The Sentinel-2 satellite images are openly and freely accessible provided in the Earth observation program Copernicus. We present a novel dataset based on Sentinel-2 satellite images covering 13 spectral bands and consisting out of 10 classes with in total 27,000 labeled and geo-referenced images. We provide benchmarks for this novel dataset with its spectral bands using state-of-the-art deep Convolutional Neural Network (CNNs). With the proposed novel dataset, we achieved an overall classification accuracy of 98.57%. The resulting classification system opens a gate towards a number of Earth observation applications. We demonstrate how this classification system can be used for detecting land use and land cover changes and how it can assist in improving geographical maps. The geo-referenced dataset EuroSAT is made publicly available at https://github.com/phelber/eurosat.
translated by 谷歌翻译
Coronary Computed Tomography Angiography (CCTA) provides information on the presence, extent, and severity of obstructive coronary artery disease. Large-scale clinical studies analyzing CCTA-derived metrics typically require ground-truth validation in the form of high-fidelity 3D intravascular imaging. However, manual rigid alignment of intravascular images to corresponding CCTA images is both time consuming and user-dependent. Moreover, intravascular modalities suffer from several non-rigid motion-induced distortions arising from distortions in the imaging catheter path. To address these issues, we here present a semi-automatic segmentation-based framework for both rigid and non-rigid matching of intravascular images to CCTA images. We formulate the problem in terms of finding the optimal \emph{virtual catheter path} that samples the CCTA data to recapitulate the coronary artery morphology found in the intravascular image. We validate our co-registration framework on a cohort of $n=40$ patients using bifurcation landmarks as ground truth for longitudinal and rotational registration. Our results indicate that our non-rigid registration significantly outperforms other co-registration approaches for luminal bifurcation alignment in both longitudinal (mean mismatch: 3.3 frames) and rotational directions (mean mismatch: 28.6 degrees). By providing a differentiable framework for automatic multi-modal intravascular data fusion, our developed co-registration modules significantly reduces the manual effort required to conduct large-scale multi-modal clinical studies while also providing a solid foundation for the development of machine learning-based co-registration approaches.
translated by 谷歌翻译