数据集的质量在成功培训和部署深度学习模型中起着至关重要的作用。特别是在系统性能可能影响患者健康状况的医疗领域，干净的数据集是可靠预测的安全要求。因此，在构建自主临床决策系统时，离群值检测是一个必不可少的过程。在这项工作中，我们评估了自组织图对外离检测的适用性，专门针对包含白细胞定量相图像的医学数据集。我们根据量化误差和距离图检测和评估异常值。我们的发现证实了自组织地图对于手头数据集的无监督分布检测的适用性。根据专家领域知识，自组织地图与手动指定的过滤器相同。此外，它们在探索和清洁医疗数据集的工具方面显示了希望。作为未来研究的方向，我们建议将自组织地图和基于深度学习的特征提取的结合。
translated by 谷歌翻译
Previous work has shown the potential of deep learning to predict renal obstruction using kidney ultrasound images. However, these image-based classifiers have been trained with the goal of single-visit inference in mind. We compare methods from video action recognition (i.e. convolutional pooling, LSTM, TSM) to adapt single-visit convolutional models to handle multiple visit inference. We demonstrate that incorporating images from a patient's past hospital visits provides only a small benefit for the prediction of obstructive hydronephrosis. Therefore, inclusion of prior ultrasounds is beneficial, but prediction based on the latest ultrasound is sufficient for patient risk stratification.
translated by 谷歌翻译
Benchmark performance of deep learning classifiers alone is not a reliable predictor for the performance of a deployed model. In particular, if the image classifier has picked up spurious features in the training data, its predictions can fail in unexpected ways. In this paper, we develop a framework that allows us to systematically identify spurious features in large datasets like ImageNet. It is based on our neural PCA components and their visualization. Previous work on spurious features of image classifiers often operates in toy settings or requires costly pixel-wise annotations. In contrast, we validate our results by checking that presence of the harmful spurious feature of a class is sufficient to trigger the prediction of that class. We introduce a novel dataset "Spurious ImageNet" and check how much existing classifiers rely on spurious features.
translated by 谷歌翻译
Transfer operators offer linear representations and global, physically meaningful features of nonlinear dynamical systems. Discovering transfer operators, such as the Koopman operator, require careful crafted dictionaries of observables, acting on states of the dynamical system. This is ad hoc and requires the full dataset for evaluation. In this paper, we offer an optimization scheme to allow joint learning of the observables and Koopman operator with online data. Our results show we are able to reconstruct the evolution and represent the global features of complex dynamical systems.
translated by 谷歌翻译
Realizing when a model is right for a wrong reason is not trivial and requires a significant effort by model developers. In some cases, an input salience method, which highlights the most important parts of the input, may reveal problematic reasoning. But scrutinizing highlights over many data instances is tedious and often infeasible. Furthermore, analyzing examples in isolation does not reveal general patterns in the data or in the model's behavior. In this paper we aim to address these issues and go from understanding single examples to understanding entire datasets and models. The methodology we propose is based on aggregated salience maps. Using this methodology we address multiple distinct but common model developer needs by showing how problematic data and model behavior can be identified -- a necessary first step for improving the model.
translated by 谷歌翻译
Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions. While these capabilities have led to widespread adoption, most LLMs are developed by resource-rich organizations and are frequently kept from the public. As a step towards democratizing this powerful technology, we present BLOOM, a 176B-parameter open-access language model designed and built thanks to a collaboration of hundreds of researchers. BLOOM is a decoder-only Transformer language model that was trained on the ROOTS corpus, a dataset comprising hundreds of sources in 46 natural and 13 programming languages (59 in total). We find that BLOOM achieves competitive performance on a wide variety of benchmarks, with stronger results after undergoing multitask prompted finetuning. To facilitate future research and applications using LLMs, we publicly release our models and code under the Responsible AI License.
translated by 谷歌翻译
创伤后应激障碍（PTSD）是一种长期衰弱的精神状况，是针对灾难性生活事件（例如军事战斗，性侵犯和自然灾害）而发展的。 PTSD的特征是过去的创伤事件，侵入性思想，噩梦，过度维护和睡眠障碍的闪回，所有这些都会影响一个人的生活，并导致相当大的社会，职业和人际关系障碍。 PTSD的诊断是由医学专业人员使用精神障碍诊断和统计手册（DSM）中定义的PTSD症状的自我评估问卷进行的。在本文中，这是我们第一次收集，注释并为公共发行准备了一个新的视频数据库，用于自动PTSD诊断，在野生数据集中称为PTSD。该数据库在采集条件下表现出“自然”和巨大的差异，面部表达，照明，聚焦，分辨率，年龄，性别，种族，遮挡和背景。除了描述数据集集合的详细信息外，我们还提供了评估野生数据集中PTSD的基于计算机视觉和机器学习方法的基准。此外，我们建议并评估基于深度学习的PTSD检测方法。提出的方法显示出非常有希望的结果。有兴趣的研究人员可以从：http：//www.lissi.fr/ptsd-dataset/下载PTSD-in-wild数据集的副本
translated by 谷歌翻译
行星漫游者任务必须利用基于机器学习的感知来继续发生地球外探索，几乎没有人类的存在。火星地形细分对于漫游车导航和避免危害至关重要，以执行进一步的探索性任务，例如土壤样品收集和寻找有机化合物。当前的火星地形细分模型需要大量标记的数据才能实现可接受的性能，还需要重新培训以在不同域中的部署，即不同的漫游者任务或不同的任务，即地质识别和导航。这项研究提出了一种半监督的学习方法，该方法利用了骨干的无监督对比度预处理，用于对火星表面的多效率语义分割。该模型将通过使用混合域训练套件来确保具有多样性的混合域训练套件，从而扩展到当前的火星分割能力，以便在不同的火星漫游者任务中部署以进行地形导航。使用平均像素精度的评估结果表明，与单个领域训练和监督培训相比，半监督的混合域方法通过达到火星科学实验室的好奇心漫游者的精度为97％，MARS 2020 Perseverance Perseverance Rover提高了精度。 。此外，使用召回度量与标准的跨透镜损失相比，使用召回度量的损失功能提供不同的权重方法将对少数族裔或稀有类别的模型提高了30％以上。这些结果可以以数据效率的方式为Rover任务提供未来的多任务和多任务语义细分。
translated by 谷歌翻译
近年来，已经开发了用于图像分类的新型体系结构组件，从变压器中使用的注意力和斑块开始。尽管先前的作品已经分析了建筑成分某些方面对对抗性攻击的鲁棒性，尤其是视觉变形金刚的影响，但对主要因素的理解仍然是有限的。我们比较了几个（非）固定分类器与不同的架构并研究其属性，包括对抗训练对学习特征的解释性和对看不见威胁模型的鲁棒性的影响。从Resnet到Convnext的消融揭示了关键的架构变化，导致$ 10 \％$更高$ \ ell_ \ ell_ \ infty $ bobustness。
translated by 谷歌翻译
对抗性补丁攻击是现实世界深度学习应用程序的新兴安全威胁。我们提出了戴定的平滑，这是第一种（符合我们的知识），以证明语义分割模型与此威胁模型的鲁棒性。以前关于防御补丁攻击的辩护的工作主要集中在图像分类任务上，并且经常需要更改模型体系结构和其他培训，而这些培训是不受欢迎且计算上昂贵的。在被删除的平滑度中，可以在没有特定培训，微调或限制体系结构的情况下应用任何分割模型。使用不同的掩盖策略，可以将拔掉的平滑措施应用于认证检测和认证恢复。在广泛的实验中，我们表明，在检测任务中，平均可以证明1％补丁的像素预测的64％，而在ADE20K数据集中恢复任务的0.5％贴片为48％。
translated by 谷歌翻译