Motivated by mitigating potentially harmful impacts of technologies, the AI community has formulated and accepted mathematical definitions for certain pillars of accountability: e.g. privacy, fairness, and model transparency. Yet, we argue this is fundamentally misguided because these definitions are imperfect, siloed constructions of the human values they hope to proxy, while giving the guise that those values are sufficiently embedded in our technologies. Under popularized methods, tensions arise when practitioners attempt to achieve each pillar of fairness, privacy, and transparency in isolation or simultaneously. In this position paper, we push for redirection. We argue that the AI community needs to consider all the consequences of choosing certain formulations of these pillars -- not just the technical incompatibilities, but also the effects within the context of deployment. We point towards sociotechnical research for frameworks for the latter, but push for broader efforts into implementing these in practice.
translated by 谷歌翻译
基于变压器的模型的出现，机器翻译已经快速发展。这些模型没有内置的明确的语言结构，但是它们仍然可以通过参与相关令牌隐式学习结构化的关系。我们假设通过明确赋予变形金刚具有结构性偏见，可以使这种结构学习变得更加健壮，我们研究了两种在这种偏见中构建的方法。一种方法，即TP变换器，可以增强传统的变压器体系结构，包括代表结构的附加组件。第二种方法通过将数据分割为形态令牌化来灌输数据级别的结构。我们测试了这些方法从英语翻译成土耳其语和Inuktitut的形态丰富的语言，并考虑自动指标和人类评估。我们发现，这两种方法中每种方法都允许网络实现更好的性能，但是此改进取决于数据集的大小。总而言之，结构编码方法使变压器更具样本效率，从而使它们能够从少量数据中表现得更好。
translated by 谷歌翻译
在非IID本地数据集的情况下，即客户数据的分布是异质的，联合学习会受到损失。应对这一挑战的一种有希望的方法是最近提出的方法Fedaux，即甚至高度异构客户数据的联合蒸馏增强，并具有强劲的结果。 Fedaux是一种部分$（\ epsilon，\ delta）$ - 差异化的私有方法，就客户的私人数据仅在其参与的部分培训中受到保护。这项工作贡献了完全差异化的私人修改，称为Fedauxfdp。我们进一步对正则化多项式逻辑回归的$ L_2 $ - 敏感性做出了贡献。在大规模图像数据集的深网实验中，具有强大差异隐私的FedauxFDP在仅在一次通信回合中，在非IID客户端数据上的其他同样私有化的SOTA基线表现出色。修改方法的完全私有化导致所有数据异质性的准确性降低可忽略不计。
translated by 谷歌翻译
深度图像置位者实现最先进的结果，但具有隐藏的成本。如最近的文献所见，这些深度网络能够过度接受其训练分布，导致将幻觉不准确地添加到输出并概括到不同的数据。为了更好地控制和解释性，我们提出了一种新颖的框架，利用了去噪网络。我们称之为可控的基于席位的图像去噪（CCID）。在此框架中，我们利用深度去噪网络的输出与通过可靠的过滤器卷积的图像一起。这样的过滤器可以是一个简单的卷积核，其不会增加添加幻觉信息。我们建议使用频域方法熔断两个组件，该方法考虑了深网络输出的可靠性。通过我们的框架，用户可以控制频域中两个组件的融合。我们还提供了一个用户友好的地图估算，空间上的置信度可能包含网络幻觉。结果表明，我们的CCID不仅提供了更多的可解释性和控制，而且甚至可以优于深脱离机构的定量性能和可靠的过滤器的定量性能，尤其是当测试数据从训练数据发散时。
translated by 谷歌翻译
在许多计算机视觉应用程序中，对高动态范围（HDR）场景的能力至关重要。然而，传统传感器的动态范围基本上受其井容量的限制，导致明亮场景部件的饱和度。为了克服这种限制，新兴传感器提供了用于编码入射辐照度的像素处理能力。在最有前途的编码方案中，模数包装，其导致计算机拍摄场景由来自包裹的低动态（LDR）传感器图像的辐照法展开算法计算的计算摄影问题。在这里，我们设计了一种基于神经网络的算法，优于先前的辐照度展示方法，更重要的是，我们设计了一种感知的激发灵感的“螳螂”编码方案，从而更有效地将HDR场景包装到LDR传感器中。结合我们的重建框架，Mantissacam在模型快照HDR成像方法中实现了最先进的结果。我们展示了我们在模拟中的效果，并显示了用可编程传感器实现的原型尾涂的初步结果。
translated by 谷歌翻译
Recently, neural networks purely based on attention were shown to address image understanding tasks such as image classification. These highperforming vision transformers are pre-trained with hundreds of millions of images using a large infrastructure, thereby limiting their adoption.In this work, we produce competitive convolution-free transformers by training on Imagenet only. We train them on a single computer in less than 3 days. Our reference vision transformer (86M parameters) achieves top-1 accuracy of 83.1% (single-crop) on ImageNet with no external data.More importantly, we introduce a teacher-student strategy specific to transformers. It relies on a distillation token ensuring that the student learns from the teacher through attention. We show the interest of this token-based distillation, especially when using a convnet as a teacher. This leads us to report results competitive with convnets for both Imagenet (where we obtain up to 85.2% accuracy) and when transferring to other tasks. We share our code and models.
translated by 谷歌翻译
Deep learning frameworks have often focused on either usability or speed, but not both. PyTorch is a machine learning library that shows that these two goals are in fact compatible: it provides an imperative and Pythonic programming style that supports code as a model, makes debugging easy and is consistent with other popular scientific computing libraries, while remaining efficient and supporting hardware accelerators such as GPUs. In this paper, we detail the principles that drove the implementation of PyTorch and how they are reflected in its architecture. We emphasize that every aspect of PyTorch is a regular Python program under the full control of its user. We also explain how the careful and pragmatic implementation of the key components of its runtime enables them to work together to achieve compelling performance. We demonstrate the efficiency of individual subsystems, as well as the overall speed of PyTorch on several common benchmarks.
translated by 谷歌翻译