Even though active learning forms an important pillar of machine learning, deep learning tools are not prevalent within it. Deep learning poses several difficulties when used in an active learning setting. First, active learning (AL) methods generally rely on being able to learn and update models from small amounts of data. Recent advances in deep learning, on the other hand, are notorious for their dependence on large amounts of data. Second, many AL acquisition functions rely on model uncertainty, yet deep learning methods rarely represent such model uncertainty. In this paper we combine recent advances in Bayesian deep learning into the active learning framework in a practical way. We develop an active learning framework for high dimensional data, a task which has been extremely challenging so far, with very sparse existing literature. Taking advantage of specialised models such as Bayesian convolutional neural networks, we demonstrate our active learning techniques with image data, obtaining a significant improvement on existing active learning approaches. We demonstrate this on both the MNIST dataset, as well as for skin cancer diagnosis from lesion images (ISIC2016 task).
translated by 谷歌翻译
We develop BatchBALD, a tractable approximation to the mutual information between a batch of points and model parameters, which we use as an acquisition function to select multiple informative points jointly for the task of deep Bayesian active learning. BatchBALD is a greedy linear-time 1 − 1 /e-approximate algorithm amenable to dynamic programming and efficient caching. We compare BatchBALD to the commonly used approach for batch data acquisition and find that the current approach acquires similar and redundant points, sometimes performing worse than randomly acquiring data. We finish by showing that, using BatchBALD to consider dependencies within an acquisition batch, we achieve new state of the art performance on standard benchmarks, providing substantial data efficiency improvements in batch acquisition.
translated by 谷歌翻译
主动学习是减少训练深神经网络模型中数据量的流行方法。它的成功取决于选择有效的采集函数,该功能尚未根据其预期的信息进行排名。在不确定性抽样中,当前模型具有关于点类标签的不确定性是这种类型排名的主要标准。本文提出了一种在培训卷积神经网络(CNN)中进行不确定性采样的新方法。主要思想是使用CNN提取提取的特征表示作为培训总产品网络(SPN)的数据。由于SPN通常用于估计数据集的分布,因此它们非常适合估算类概率的任务,这些概率可以直接由标准采集函数(例如最大熵和变异比率)使用。此外,我们通过在SPN模型的帮助下通过权重增强了这些采集函数。这些权重使采集功能对数据点的可疑类标签的多样性更加敏感。我们的方法的有效性在对MNIST,时尚持续和CIFAR-10数据集的实验研究中得到了证明,我们将其与最先进的方法MC辍学和贝叶斯批次进行了比较。
translated by 谷歌翻译
主动学习在许多领域中展示了数据效率。现有的主动学习算法,特别是在深贝叶斯活动模型的背景下,严重依赖模型的不确定性估计的质量。然而,这种不确定性估计可能会严重偏见,特别是有限和不平衡的培训数据。在本文中,我们建议平衡,贝叶斯深度活跃的学习框架,减轻这种偏差的影响。具体地,平衡采用了一种新的采集功能,该函数利用了等效假设类别捕获的结构,并促进了不同的等价类别之间的分化。直观地,每个等价类包括具有类似预测的深层模型的实例化,并且平衡适应地将等同类的大小调整为学习进展。除了完整顺序设置之外,我们还提出批量平衡 - 顺序算法的泛化算法到批量设置 - 有效地选择批次的培训实施例,这些培训实施例是对模型改进的联合有效的培训实施例。我们展示批量平衡在多个基准数据集上实现了最先进的性能,用于主动学习,并且这两个算法都可以有效地处理通常涉及多级和不平衡数据的逼真挑战。
translated by 谷歌翻译
在Mackay(1992)上展开,我们认为,用于主动学习的基于模式的方法 - 类似的基于模型 - 如秃顶 - 具有基本的缺点:它们未直接解释输入变量的测试时间分布。这可以导致采集策略中的病理,因为模型参数的最大信息是最大信息,可能不是最大地信息,例如,当池集中的数据比最终预测任务的数据更大时,或者池和试验样品的分布不同。为了纠正这一点,我们重新审视了基于最大化关于可能的未来预测的预期信息的收购策略,参考这是预期的预测信息增益(EPIG)。由于EPIG对批量采集不扩展,我们进一步检查了替代策略,秃头和EPIG之间的混合,我们称之为联合预测信息增益(Jepig)。我们考虑在各种数据集中使用贝叶斯神经网络的主动学习,检查池集中分布班下的行为。
translated by 谷歌翻译
The generalisation performance of a convolutional neural networks (CNN) is majorly predisposed by the quantity, quality, and diversity of the training images. All the training data needs to be annotated in-hand before, in many real-world applications data is easy to acquire but expensive and time-consuming to label. The goal of the Active learning for the task is to draw most informative samples from the unlabeled pool which can used for training after annotation. With total different objective, self-supervised learning which have been gaining meteoric popularity by closing the gap in performance with supervised methods on large computer vision benchmarks. self-supervised learning (SSL) these days have shown to produce low-level representations that are invariant to distortions of the input sample and can encode invariance to artificially created distortions, e.g. rotation, solarization, cropping etc. self-supervised learning (SSL) approaches rely on simpler and more scalable frameworks for learning. In this paper, we unify these two families of approaches from the angle of active learning using self-supervised learning mainfold and propose Deep Active Learning using BarlowTwins(DALBT), an active learning method for all the datasets using combination of classifier trained along with self-supervised loss framework of Barlow Twins to a setting where the model can encode the invariance of artificially created distortions, e.g. rotation, solarization, cropping etc.
translated by 谷歌翻译
在主动学习中,训练数据集的大小和复杂性随时间而变化。随着更多要点,由主动学习开始时可用的数据量良好的简单模型可能会受到偏见的影响。可能非常适合于完整数据集的灵活模型可能会在积极学习开始时受到过度装备。我们使用深度不确定性网络(DUNS)来解决这个问题,其中一个BNN变体,其中网络的深度以及其复杂性。我们发现DUNS在几个活跃的学习任务上表现出其他BNN变体。重要的是,我们表明,在DUNs表现最佳的任务上,它们呈现出比基线的显着不太容易。
translated by 谷歌翻译
Acquiring labeled data is challenging in many machine learning applications with limited budgets. Active learning gives a procedure to select the most informative data points and improve data efficiency by reducing the cost of labeling. The info-max learning principle maximizing mutual information such as BALD has been successful and widely adapted in various active learning applications. However, this pool-based specific objective inherently introduces a redundant selection and further requires a high computational cost for batch selection. In this paper, we design and propose a new uncertainty measure, Balanced Entropy Acquisition (BalEntAcq), which captures the information balance between the uncertainty of underlying softmax probability and the label variable. To do this, we approximate each marginal distribution by Beta distribution. Beta approximation enables us to formulate BalEntAcq as a ratio between an augmented entropy and the marginalized joint entropy. The closed-form expression of BalEntAcq facilitates parallelization by estimating two parameters in each marginal Beta distribution. BalEntAcq is a purely standalone measure without requiring any relational computations with other data points. Nevertheless, BalEntAcq captures a well-diversified selection near the decision boundary with a margin, unlike other existing uncertainty measures such as BALD, Entropy, or Mean Standard Deviation (MeanSD). Finally, we demonstrate that our balanced entropy learning principle with BalEntAcq consistently outperforms well-known linearly scalable active learning methods, including a recently proposed PowerBALD, a simple but diversified version of BALD, by showing experimental results obtained from MNIST, CIFAR-100, SVHN, and TinyImageNet datasets.
translated by 谷歌翻译
尽管基于卷积神经网络(CNN)的组织病理学图像的分类模型,但量化其不确定性是不可行的。此外,当数据偏置时,CNN可以遭受过度装备。我们展示贝叶斯-CNN可以通过自动规范并通过量化不确定性来克服这些限制。我们开发了一种新颖的技术,利用贝叶斯-CNN提供的不确定性,这显着提高了大部分测试数据的性能(约为77%的测试数据的准确性提高了约6%)。此外,我们通过非线性维度降低技术将数据投射到低尺寸空间来提供对不确定性的新颖解释。该维度降低能够通过可视化解释测试数据,并在低维特征空间中揭示数据的结构。我们表明,贝叶斯-CNN可以通过分别将假阴性和假阳性降低11%和7.7%的最先进的转移学习CNN(TL-CNN)来表现出远得更好。它具有仅为186万个参数的这种性能,而TL-CNN的参数仅为134.33亿。此外,我们通过引入随机自适应激活功能来修改贝叶斯-CNN。修改后的贝叶斯-CNN在所有性能指标上的贝叶斯-CNN略胜一筹,并显着降低了误报和误报的数量(两者减少了3%)。我们还表明,通过执行McNemar的统计显着性测试,这些结果具有统计学意义。这项工作显示了贝叶斯-CNN对现有技术的优势,解释并利用组织病理学图像的不确定性。它应该在各种医学图像分类中找到应用程序。
translated by 谷歌翻译
大型,注释的数据集在医学图像分析中不广泛使用,这是由于时间,成本和标记大型数据集相关的挑战。未标记的数据集更容易获取,在许多情况下,专家可以为一小部分图像提供标签是可行的。这项工作提出了一个信息理论的主动学习框架,该框架可以根据评估数据集中最大化预期信息增益(EIG)来指导未标记池的最佳图像选择。实验是在两个不同的医学图像分类数据集上进行的:多类糖尿病性视网膜病变量表分类和多级皮肤病变分类。结果表明,通过调整EIG来说明班级不平衡,我们提出的适应预期信息增益(AEIG)的表现优于几个流行的基线,包括基于多样性的核心和基于不确定性的最大熵抽样。具体而言,AEIG仅占总体表现的95%,只有19%的培训数据,而其他活跃的学习方法则需要约25%。我们表明,通过仔细的设计选择,我们的模型可以集成到现有的深度学习分类器中。
translated by 谷歌翻译
Deep learning tools have gained tremendous attention in applied machine learning. However such tools for regression and classification do not capture model uncertainty. In comparison, Bayesian models offer a mathematically grounded framework to reason about model uncertainty, but usually come with a prohibitive computational cost. In this paper we develop a new theoretical framework casting dropout training in deep neural networks (NNs) as approximate Bayesian inference in deep Gaussian processes. A direct result of this theory gives us tools to model uncertainty with dropout NNsextracting information from existing models that has been thrown away so far. This mitigates the problem of representing uncertainty in deep learning without sacrificing either computational complexity or test accuracy. We perform an extensive study of the properties of dropout's uncertainty. Various network architectures and nonlinearities are assessed on tasks of regression and classification, using MNIST as an example. We show a considerable improvement in predictive log-likelihood and RMSE compared to existing state-of-the-art methods, and finish by using dropout's uncertainty in deep reinforcement learning.
translated by 谷歌翻译
标记数据可以是昂贵的任务,因为它通常由域专家手动执行。对于深度学习而言,这是繁琐的,因为它取决于大型标记的数据集。主动学习(AL)是一种范式,旨在通过仅使用二手车型认为最具信息丰富的数据来减少标签努力。在文本分类设置中,在AL上完成了很少的研究,旁边没有涉及最近的最先进的自然语言处理(NLP)模型。在这里,我们介绍了一个实证研究,可以将基于不确定性的基于不确定性的算法与Bert $ _ {base} $相比,作为使用的分类器。我们评估两个NLP分类数据集的算法:斯坦福情绪树木银行和kvk-Front页面。此外,我们探讨了旨在解决不确定性的al的预定问题的启发式;即,它是不可规范的,并且易于选择异常值。此外,我们探讨了查询池大小对al的性能的影响。虽然发现,AL的拟议启发式没有提高AL的表现;我们的结果表明,使用BERT $ _ {Base} $概率使用不确定性的AL。随着查询池大小变大,性能的这种差异可以减少。
translated by 谷歌翻译
在这项工作中,我们使用变分推论来量化无线电星系分类的深度学习模型预测的不确定性程度。我们表明,当标记无线电星系时,个体测试样本的模型后差水平与人类不确定性相关。我们探讨了各种不同重量前沿的模型性能和不确定性校准,并表明稀疏事先产生更良好的校准不确定性估计。使用单个重量的后部分布,我们表明我们可以通过从最低信噪比(SNR)中除去权重来修剪30%的完全连接的层权重,而无需显着损失性能。我们证明,可以使用基于Fisher信息的排名来实现更大程度的修剪,但我们注意到两种修剪方法都会影响Failaroff-Riley I型和II型无线电星系的不确定性校准。最后,我们表明,与此领域的其他工作相比,我们经历了冷的后效,因此后部必须缩小后加权以实现良好的预测性能。我们检查是否调整成本函数以适应模型拼盘可以弥补此效果,但发现它不会产生显着差异。我们还研究了原则数据增强的效果,并发现这改善了基线,而且还没有弥补观察到的效果。我们将其解释为寒冷的后效,因为我们的培训样本过于有效的策划导致可能性拼盘,并将其提高到未来无线电银行分类的潜在问题。
translated by 谷歌翻译
There are two major types of uncertainty one can model. Aleatoric uncertainty captures noise inherent in the observations. On the other hand, epistemic uncertainty accounts for uncertainty in the model -uncertainty which can be explained away given enough data. Traditionally it has been difficult to model epistemic uncertainty in computer vision, but with new Bayesian deep learning tools this is now possible. We study the benefits of modeling epistemic vs. aleatoric uncertainty in Bayesian deep learning models for vision tasks. For this we present a Bayesian deep learning framework combining input-dependent aleatoric uncertainty together with epistemic uncertainty. We study models under the framework with per-pixel semantic segmentation and depth regression tasks. Further, our explicit uncertainty formulation leads to new loss functions for these tasks, which can be interpreted as learned attenuation. This makes the loss more robust to noisy data, also giving new state-of-the-art results on segmentation and depth regression benchmarks.
translated by 谷歌翻译
As an important data selection schema, active learning emerges as the essential component when iterating an Artificial Intelligence (AI) model. It becomes even more critical given the dominance of deep neural network based models, which are composed of a large number of parameters and data hungry, in application. Despite its indispensable role for developing AI models, research on active learning is not as intensive as other research directions. In this paper, we present a review of active learning through deep active learning approaches from the following perspectives: 1) technical advancements in active learning, 2) applications of active learning in computer vision, 3) industrial systems leveraging or with potential to leverage active learning for data iteration, 4) current limitations and future research directions. We expect this paper to clarify the significance of active learning in a modern AI model manufacturing process and to bring additional research attention to active learning. By addressing data automation challenges and coping with automated machine learning systems, active learning will facilitate democratization of AI technologies by boosting model production at scale.
translated by 谷歌翻译
估算高维观测数据的个性化治疗效果在实验设计不可行,不道德或昂贵的情况下是必不可少的。现有方法依赖于拟合对治疗和控制人群的结果的深层模型。然而,当测量单独的结果是昂贵的时,就像肿瘤活检一样,需要一种用于获取每种结果的样本有效的策略。深度贝叶斯主动学习通过选择具有高不确定性的点来提供高效数据采集的框架。然而,现有方法偏置训练数据获取对处理和控制群体之间的非重叠支持区域。这些不是样本效率,因为在这些区域中不可识别治疗效果。我们介绍了因果关系,贝叶斯采集函数接地的信息理论,使数据采集朝向具有重叠支持的地区,以最大限度地提高学习个性化治疗效果的采样效率。我们展示了拟议的综合和半合成数据集IHDP和CMNIST上提出的收购策略及其扩展的表现,旨在模拟常见的数据集偏差和病理学。
translated by 谷歌翻译
人工智能(AI)辅助方法在风险领域(例如疾病诊断)受到了很多关注。与疾病类型的分类不同,将医学图像归类为良性或恶性肿瘤是一项精细的任务。但是,大多数研究仅着重于提高诊断准确性,而忽略了模型可靠性的评估,从而限制了其临床应用。对于临床实践,校准对过度参数化的模型和固有的噪声极为明显地提出了低数据表格的主要挑战。特别是,我们发现建模与数据相关的不确定性更有利于置信度校准。与测试时间增强(TTA)相比,我们通过混合数据增强策略提出了一个修改后的自举损失(BS损耗)功能,可以更好地校准预测性不确定性并捕获数据分布转换而无需额外推断时间。我们的实验表明,与标准数据增强,深度集合和MC辍学相比,混合(BSM)模型的BS损失(BSM)模型可以将预期校准误差(ECE)减半。在BSM模型下,不确定性与相似性之间的相关性高达-0.4428。此外,BSM模型能够感知室外数据的语义距离,这表明在现实世界中的临床实践中潜力很高。
translated by 谷歌翻译
现代深度学习方法构成了令人难以置信的强大工具,以解决无数的挑战问题。然而,由于深度学习方法作为黑匣子运作,因此与其预测相关的不确定性往往是挑战量化。贝叶斯统计数据提供了一种形式主义来理解和量化与深度神经网络预测相关的不确定性。本教程概述了相关文献和完整的工具集,用于设计,实施,列车,使用和评估贝叶斯神经网络,即使用贝叶斯方法培训的随机人工神经网络。
translated by 谷歌翻译
深度学习方法实现了对放射学图像进行分类的最新性能,但依赖于需要专家资源密集型注释的大型标签数据集。半监督学习和积极学习都可以用于减轻这种注释负担。但是,对于多标签医学图像分类,将半监督和主动学习方法的优势结合起来的工作有限。在这里,我们介绍了一种基于一致性的新型半监督证据活跃学习框架(CSEAL)。具体而言,我们利用基于证据和主观逻辑理论的预测不确定性来开发一种端到端的综合方法,该方法将基于一致性的半监督学习与基于不确定性的主动学习相结合。我们采用我们的方法来增强四种基于一致性的半监督学习方法:伪标记,虚拟对抗性培训,卑鄙的老师和不老师。对多标签胸部X射线分类任务的广泛评估表明,CSEAL在两个领先的半监督活跃学习基线方面取得了实质性改进。此外,班级分解的结果表明,我们的方法可以大大提高标记样品较少的稀有异常的准确性。
translated by 谷歌翻译
卷积神经网络(CNN)的泛化性能受训练图像的数量,质量和品种的影响。必须注释训练图像,这是耗时和昂贵的。我们工作的目标是减少培训CNN所需的注释图像的数量,同时保持其性能。我们假设通过确保该组训练图像包含大部分难以分类的图像,可以更快地提高CNN的性能。我们的研究目的是使用活动学习方法测试这个假设,可以自动选择难以分类的图像。我们开发了一种基于掩模区域的CNN(掩模R-CNN)的主动学习方法,并命名此方法Maskal。 Maskal涉及掩模R-CNN的迭代训练,之后培训的模型用于选择一组未标记的图像,该模型是不确定的。然后将所选择的图像注释并用于恢复掩模R-CNN,并且重复这一点用于许多采样迭代。在我们的研究中,掩模R-CNN培训由由12个采样迭代选择的2500个硬花甘蓝图像,从训练组14,000个硬花甘蓝图像的训练组中选择了12个采样迭代。对于所有采样迭代,Maskal比随机采样显着更好。此外,在抽样900图像之后,屏蔽具有相同的性能,随着随机抽样在2300张图像之后。与在整个培训集(14,000张图片)上培训的面具R-CNN模型相比,Maskal达到其性能的93.9%,其培训数据的17.9%。随机抽样占其性能的81.9%,占其培训数据的16.4%。我们得出结论,通过使用屏马,可以减少注释工作对于在西兰花的数据集上训练掩模R-CNN。我们的软件可在https://github.com/pieterblok/maskal上找到。
translated by 谷歌翻译