在深度学习的生态系统中,嘈杂的标签是不可避免的,但很麻烦,因为模型可以轻松地过度拟合它们。标签噪声有许多类型,例如对称,不对称和实例依赖性噪声(IDN),而IDN是唯一取决于图像信息的类型。鉴于标签错误很大程度上是由于图像中存在的视觉类别不足或模棱两可的信息引起的,因此对图像信息的这种依赖性使IDN成为可研究标签噪声的关键类型。为了提供一种有效的技术来解决IDN,我们提出了一种称为InstanceGM的新图形建模方法,该方法结合了判别和生成模型。实例GM的主要贡献是:i)使用连续的Bernoulli分布来培训生成模型,提供了重要的培训优势,ii)探索最先进的噪声标签歧视分类器来生成清洁标签来自实例依赖性嘈杂标签样品。 InstanceGM具有当前嘈杂的学习方法的竞争力,尤其是在使用合成和现实世界数据集的IDN基准测试中,我们的方法比大多数实验中的竞争对手都表现出更好的准确性。
translated by 谷歌翻译
Learning with noisy-labels has become an important research topic in computer vision where state-of-the-art (SOTA) methods explore: 1) prediction disagreement with co-teaching strategy that updates two models when they disagree on the prediction of training samples; and 2) sample selection to divide the training set into clean and noisy sets based on small training loss. However, the quick convergence of co-teaching models to select the same clean subsets combined with relatively fast overfitting of noisy labels may induce the wrong selection of noisy label samples as clean, leading to an inevitable confirmation bias that damages accuracy. In this paper, we introduce our noisy-label learning approach, called Asymmetric Co-teaching (AsyCo), which introduces novel prediction disagreement that produces more consistent divergent results of the co-teaching models, and a new sample selection approach that does not require small-loss assumption to enable a better robustness to confirmation bias than previous methods. More specifically, the new prediction disagreement is achieved with the use of different training strategies, where one model is trained with multi-class learning and the other with multi-label learning. Also, the new sample selection is based on multi-view consensus, which uses the label views from training labels and model predictions to divide the training set into clean and noisy for training the multi-class model and to re-label the training samples with multiple top-ranked labels for training the multi-label model. Extensive experiments on synthetic and real-world noisy-label datasets show that AsyCo improves over current SOTA methods.
translated by 谷歌翻译
元学习是一种处理不平衡和嘈杂标签学习的有效方法,但它取决于验证集,其中包含随机选择,手动标记和平衡的分布式样品。该验证集的随机选择和手动标记和平衡不仅是元学习的最佳选择,而且随着类的数量,它的缩放范围也很差。因此,最近的元学习论文提出了临时启发式方法来自动构建和标记此验证集,但是这些启发式方法仍然是元学习的最佳选择。在本文中,我们分析了元学习算法,并提出了新的标准来表征验证集的实用性,基于:1)验证集的信息性; 2)集合的班级分配余额; 3)集合标签的正确性。此外,我们提出了一种新的不平衡的嘈杂标签元学习(INOLML)算法,该算法会自动构建通过上面的标准最大化其实用程序来构建验证。我们的方法比以前的元学习方法显示出显着改进,并在几个基准上设定了新的最新技术。
translated by 谷歌翻译
深度神经网络模型对有限的标签噪声非常强大,但是它们在高噪声率问题中记住嘈杂标签的能力仍然是一个空旷的问题。最具竞争力的嘈杂标签学习算法依赖于一个2阶段的过程,其中包括无监督的学习,将培训样本分类为清洁或嘈杂,然后是半监督的学习,将经验仿生风险(EVR)最小化,该学习使用标记的集合制成的集合。样品被归类为干净,并提供了一个未标记的样品,该样品被分类为嘈杂。在本文中,我们假设这种2阶段嘈杂标签的学习方法的概括取决于无监督分类器的精度以及训练设置的大小以最大程度地减少EVR。我们从经验上验证了这两个假设,并提出了新的2阶段嘈杂标签训练算法longRemix。我们在嘈杂的标签基准CIFAR-10,CIFAR-100,Webvision,Clotsing1m和Food101-N上测试Longremix。结果表明,我们的Longremix比竞争方法更好,尤其是在高标签噪声问题中。此外,我们的方法在大多数数据集中都能达到最先进的性能。该代码可在https://github.com/filipe-research/longremix上获得。
translated by 谷歌翻译
Deep neural networks are known to be annotation-hungry. Numerous efforts have been devoted to reducing the annotation cost when learning with deep networks. Two prominent directions include learning with noisy labels and semi-supervised learning by exploiting unlabeled data. In this work, we propose DivideMix, a novel framework for learning with noisy labels by leveraging semi-supervised learning techniques. In particular, DivideMix models the per-sample loss distribution with a mixture model to dynamically divide the training data into a labeled set with clean samples and an unlabeled set with noisy samples, and trains the model on both the labeled and unlabeled data in a semi-supervised manner. To avoid confirmation bias, we simultaneously train two diverged networks where each network uses the dataset division from the other network. During the semi-supervised training phase, we improve the MixMatch strategy by performing label co-refinement and label co-guessing on labeled and unlabeled samples, respectively. Experiments on multiple benchmark datasets demonstrate substantial improvements over state-of-the-art methods. Code is available at https://github.com/LiJunnan1992/DivideMix.
translated by 谷歌翻译
可以将监督学习视为将相关信息从输入数据中提取到特征表示形式。当监督嘈杂时,此过程变得困难,因为蒸馏信息可能无关紧要。实际上,最近的研究表明,网络可以轻松地过度贴合所有标签,包括损坏的标签,因此几乎无法概括以清洁数据集。在本文中,我们专注于使用嘈杂的标签学习的问题,并将压缩归纳偏置引入网络体系结构以减轻这种过度的问题。更确切地说,我们重新审视一个名为辍学的经典正则化及其变体嵌套辍学。辍学可以作为其功能删除机制的压缩约束,而嵌套辍学进一步学习有序的特征表示W.R.T.特征重要性。此外,具有压缩正则化的训练有素的模型与共同教学相结合,以提高性能。从理论上讲,我们在压缩正则化下对目标函数进行偏置变化分解。我们分析了单个模型和共同教学。该分解提供了三个见解:(i)表明过度合适确实是使用嘈杂标签学习的问题; (ii)通过信息瓶颈配方,它解释了为什么提出的特征压缩有助于对抗标签噪声; (iii)它通过将压缩正规化纳入共同教学而带来的性能提升提供了解释。实验表明,我们的简单方法比具有现实世界标签噪声(包括服装1M和Animal-10N)的基准测试标准的最先进方法具有可比性甚至更好的性能。我们的实施可在https://yingyichen-cyy.github.io/compressfatsfeatnoisylabels/上获得。
translated by 谷歌翻译
尽管对神经网络进行了监督学习的巨大进展,但在获得高质量,大规模和准确标记的数据集中存在重大挑战。在这种情况下,在本文中,我们在存在标签噪声的情况下解决分类问题,更具体地,既有闭合和开放式标签噪声,就是样本的真实标签或可能不属于时给定标签的集合。在我们的方法中,方法是一种样本选择机制,其依赖于样本的注释标签与其邻域中标签的分布之间的一致性;依赖于分类器跨后续迭代的置信机制的依赖标签机制;以及培训编码器的培训策略,同时通过单独的选择样本上的跨熵丢失和分类器编码器培训。没有钟声和口哨,如共同训练,以便减少自我确认偏差,并且对其少数超参数的环境具有鲁棒性,我们的方法显着超越了与人工噪声和真实的CIFAR10 / CIFAR100上的先前方法-world噪声数据集如webvision和动物-10n。
translated by 谷歌翻译
标签噪声显着降低了应用中深度模型的泛化能力。有效的策略和方法,\ Texit {例如}重新加权或损失校正,旨在在训练神经网络时缓解标签噪声的负面影响。这些现有的工作通常依赖于预指定的架构并手动调整附加的超参数。在本文中,我们提出了翘曲的概率推断(WARPI),以便在元学习情景中自适应地整理分类网络的培训程序。与确定性模型相比,WARPI通过学习摊销元网络来制定为分层概率模型,这可以解决样本模糊性,因此对严格的标签噪声更加坚固。与直接生成损耗的重量值的现有近似加权功能不同,我们的元网络被学习以估计从登录和标签的输入来估计整流向量,这具有利用躺在它们中的足够信息的能力。这提供了纠正分类网络的学习过程的有效方法,证明了泛化能力的显着提高。此外,可以将整流载体建模为潜在变量并学习元网络,可以无缝地集成到分类网络的SGD优化中。我们在嘈杂的标签上评估了四个强大学习基准的Warpi,并在变体噪声类型下实现了新的最先进的。广泛的研究和分析还展示了我们模型的有效性。
translated by 谷歌翻译
带有嘈杂标签的训练深神经网络(DNN)实际上是具有挑战性的,因为不准确的标签严重降低了DNN的概括能力。以前的努力倾向于通过识别带有粗糙的小损失标准来减轻嘈杂标签的干扰的嘈杂数据来处理统一的denoising流中的零件或完整数据,而忽略了嘈杂样本的困难是不同的,因此是刚性和统一的。数据选择管道无法很好地解决此问题。在本文中,我们首先提出了一种称为CREMA的粗到精细的稳健学习方法,以分裂和串扰的方式处理嘈杂的数据。在粗糙水平中,干净和嘈杂的集合首先从统计意义上就可信度分开。由于实际上不可能正确对所有嘈杂样本进行分类,因此我们通过对每个样本的可信度进行建模来进一步处理它们。具体而言,对于清洁集,我们故意设计了一种基于内存的调制方案,以动态调整每个样本在训练过程中的历史可信度顺序方面的贡献,从而减轻了错误地分组为清洁集中的嘈杂样本的效果。同时,对于分类为嘈杂集的样品,提出了选择性标签更新策略,以纠正嘈杂的标签,同时减轻校正错误的问题。广泛的实验是基于不同方式的基准,包括图像分类(CIFAR,Clothing1M等)和文本识别(IMDB),具有合成或自然语义噪声,表明CREMA的优势和普遍性。
translated by 谷歌翻译
作为标签噪声,最受欢迎的分布变化之一,严重降低了深度神经网络的概括性能,具有嘈杂标签的强大训练正在成为现代深度学习中的重要任务。在本文中,我们提出了我们的框架,在子分类器(ALASCA)上创造了自适应标签平滑,该框架提供了具有理论保证和可忽略的其他计算的可靠特征提取器。首先,我们得出标签平滑(LS)会产生隐式Lipschitz正则化(LR)。此外,基于这些推导,我们将自适应LS(ALS)应用于子分类器架构上,以在中间层上的自适应LR的实际应用。我们对ALASCA进行了广泛的实验,并将其与以前的几个数据集上的噪声燃烧方法相结合,并显示我们的框架始终优于相应的基线。
translated by 谷歌翻译
The existence of label noise imposes significant challenges (e.g., poor generalization) on the training process of deep neural networks (DNN). As a remedy, this paper introduces a permutation layer learning approach termed PermLL to dynamically calibrate the training process of the DNN subject to instance-dependent and instance-independent label noise. The proposed method augments the architecture of a conventional DNN by an instance-dependent permutation layer. This layer is essentially a convex combination of permutation matrices that is dynamically calibrated for each sample. The primary objective of the permutation layer is to correct the loss of noisy samples mitigating the effect of label noise. We provide two variants of PermLL in this paper: one applies the permutation layer to the model's prediction, while the other applies it directly to the given noisy label. In addition, we provide a theoretical comparison between the two variants and show that previous methods can be seen as one of the variants. Finally, we validate PermLL experimentally and show that it achieves state-of-the-art performance on both real and synthetic datasets.
translated by 谷歌翻译
Deep Neural Networks (DNNs) have been shown to be susceptible to memorization or overfitting in the presence of noisily-labelled data. For the problem of robust learning under such noisy data, several algorithms have been proposed. A prominent class of algorithms rely on sample selection strategies wherein, essentially, a fraction of samples with loss values below a certain threshold are selected for training. These algorithms are sensitive to such thresholds, and it is difficult to fix or learn these thresholds. Often, these algorithms also require information such as label noise rates which are typically unavailable in practice. In this paper, we propose an adaptive sample selection strategy that relies only on batch statistics of a given mini-batch to provide robustness against label noise. The algorithm does not have any additional hyperparameters for sample selection, does not need any information on noise rates and does not need access to separate data with clean labels. We empirically demonstrate the effectiveness of our algorithm on benchmark datasets.
translated by 谷歌翻译
自数据注释(尤其是对于大型数据集)以来,使用嘈杂的标签学习引起了很大的研究兴趣,这可能不可避免地不可避免。最近的方法通过将培训样本分为清洁和嘈杂的集合来求助于半监督的学习问题。然而,这种范式在重标签噪声下容易出现重大变性,因为干净样品的数量太小,无法进行常规方法。在本文中,我们介绍了一个新颖的框架,称为LC-Booster,以在极端噪音下明确处理学习。 LC-Booster的核心思想是将标签校正纳入样品选择中,以便可以通过可靠的标签校正来培训更纯化的样品,从而减轻确认偏差。实验表明,LC-Booster在几个嘈杂标签的基准测试中提高了最先进的结果,包括CIFAR-10,CIFAR-100,CLASTINGING 1M和WEBVISION。值得注意的是,在极端的90 \%噪声比下,LC-Booster在CIFAR-10和CIFAR-100上获得了92.9 \%和48.4 \%的精度,超过了最终方法,较大的边距就超过了最终方法。
translated by 谷歌翻译
深度学习在大量大数据的帮助下取得了众多域中的显着成功。然而,由于许多真实情景中缺乏高质量标签,数据标签的质量是一个问题。由于嘈杂的标签严重降低了深度神经网络的泛化表现,从嘈杂的标签(强大的培训)学习是在现代深度学习应用中成为一项重要任务。在本调查中,我们首先从监督的学习角度描述了与标签噪声学习的问题。接下来,我们提供62项最先进的培训方法的全面审查,所有这些培训方法都按照其方法论差异分为五个群体,其次是用于评估其优越性的六种性质的系统比较。随后,我们对噪声速率估计进行深入分析,并总结了通常使用的评估方法,包括公共噪声数据集和评估度量。最后,我们提出了几个有前途的研究方向,可以作为未来研究的指导。所有内容将在https://github.com/songhwanjun/awesome-noisy-labels提供。
translated by 谷歌翻译
深神经网络(DNN)的记忆效果在许多最先进的标签噪声学习方法中起着枢轴作用。为了利用这一财产,通常采用早期停止训练早期优化的伎俩。目前的方法通常通过考虑整个DNN来决定早期停止点。然而,DNN可以被认为是一系列层的组成,并且发现DNN中的后一个层对标签噪声更敏感,而其前同行是非常稳健的。因此,选择整个网络的停止点可以使不同的DNN层对抗彼此影响,从而降低最终性能。在本文中,我们建议将DNN分离为不同的部位,逐步培训它们以解决这个问题。而不是早期停止,它一次列举一个整体DNN,我们最初通过用相对大量的时期优化DNN来训练前DNN层。在培训期间,我们通过使用较少数量的时期使用较少的地层来逐步培训后者DNN层,以抵消嘈杂标签的影响。我们将所提出的方法术语作为渐进式早期停止(PES)。尽管其简单性,与早期停止相比,PES可以帮助获得更有前景和稳定的结果。此外,通过将PE与现有的嘈杂标签培训相结合,我们在图像分类基准上实现了最先进的性能。
translated by 谷歌翻译
现实世界的面部表达识别(FER)数据集遭受吵闹的注释,由于众包,表达式的歧义,注释者的主观性和类间的相似性。但是,最近的深层网络具有强大的能力,可以记住嘈杂的注释导致腐蚀功能嵌入和泛化不良的能力。为了处理嘈杂的注释,我们提出了一个动态FER学习框架(DNFER),其中根据训练过程中的动态类特定阈值选择了干净的样品。具体而言,DNFER基于使用选定的干净样品和使用所有样品的无监督培训的监督培训。在训练过程中,每个微型批次的平均后类概率被用作动态类特异性阈值,以选择干净的样品进行监督训练。该阈值与噪声率无关,与其他方法不同,不需要任何干净的数据。此外,要从所有样品中学习,使用无监督的一致性损失对齐弱调节图像和强大图像之间的后验分布。我们证明了DNFER在合成和实际噪声注释的FER数据集(如RaFDB,Ferplus,Sfew和altimpnet)上的鲁棒性。
translated by 谷歌翻译
经过嘈杂标签训练的深层模型很容易在概括中过度拟合和挣扎。大多数现有的解决方案都是基于理想的假设,即标签噪声是类条件,即同一类的实例共享相同的噪声模型,并且独立于特征。在实践中,现实世界中的噪声模式通常更为细粒度作为实例依赖性,这构成了巨大的挑战,尤其是在阶层间失衡的情况下。在本文中,我们提出了一种两阶段的干净样品识别方法,以应对上述挑战。首先,我们采用类级特征聚类程序,以早期识别在班级预测中心附近的干净样品。值得注意的是,我们根据稀有类的预测熵来解决类不平衡问题。其次,对于接近地面真相类边界的其余清洁样品(通常与样品与实例有关的噪声混合),我们提出了一种基于一致性的新型分类方法,该方法使用两个分类器头的一致性来识别它们:一致性越高,样品清洁的可能性就越大。对几个具有挑战性的基准进行了广泛的实验,证明了我们的方法与最先进的方法相比。
translated by 谷歌翻译
深神经网络(DNN)的记忆效应在最近的标签噪声学习方法中起关键作用。为了利用这种效果,已经广泛采用了基于模型预测的方法,该方法旨在利用DNN在学习的早期阶段以纠正嘈杂标签的效果。但是,我们观察到该模型在标签预测期间会犯错误,从而导致性能不令人满意。相比之下,在学习早期阶段产生的特征表现出更好的鲁棒性。受到这一观察的启发,在本文中,我们提出了一种基于特征嵌入的新方法,用于用标签噪声,称为标签NoissiLution(Lend)。要具体而言,我们首先根据当前的嵌入式特征计算一个相似性矩阵,以捕获训练数据的局部结构。然后,附近标记的数据(\ textIt {i.e。},标签噪声稀释)使错误标记的数据携带的嘈杂的监督信号淹没了,其有效性是由特征嵌入的固有鲁棒性保证的。最后,带有稀释标签的培训数据进一步用于培训强大的分类器。从经验上讲,我们通过将我们的贷款与几种代表性的强大学习方法进行比较,对合成和现实世界嘈杂数据集进行了广泛的实验。结果验证了我们贷款的有效性。
translated by 谷歌翻译
The development of deep learning based image representation learning (IRL) methods has attracted great attention in the context of remote sensing (RS) image understanding. Most of these methods require the availability of a high quantity and quality of annotated training images, which can be time-consuming and costly to gather. To reduce labeling costs, publicly available thematic maps, automatic labeling procedures or crowdsourced data can be used. However, such approaches increase the risk of including label noise in training data. It may result in overfitting on noisy labels when discriminative reasoning is employed as in most of the existing methods. This leads to sub-optimal learning procedures, and thus inaccurate characterization of RS images. In this paper, as a first time in RS, we introduce a generative reasoning integrated label noise robust representation learning (GRID) approach. GRID aims to model the complementary characteristics of discriminative and generative reasoning for IRL under noisy labels. To this end, we first integrate generative reasoning into discriminative reasoning through a variational autoencoder. This allows our approach to automatically detect training samples with noisy labels. Then, through our label noise robust hybrid representation learning strategy, GRID adjusts the whole learning procedure for IRL of these samples through generative reasoning and that of the other samples through discriminative reasoning. Our approach learns discriminative image representations while preventing interference of noisy labels during training independently from the IRL method. Thus, unlike the existing methods, GRID does not depend on the type of annotation, label noise, neural network, loss or learning task, and thus can be utilized for various RS image understanding problems. Experimental results show the effectiveness of GRID compared to state-of-the-art methods.
translated by 谷歌翻译
Semi-supervised learning based methods are current SOTA solutions to the noisy-label learning problem, which rely on learning an unsupervised label cleaner first to divide the training samples into a labeled set for clean data and an unlabeled set for noise data. Typically, the cleaner is obtained via fitting a mixture model to the distribution of per-sample training losses. However, the modeling procedure is \emph{class agnostic} and assumes the loss distributions of clean and noise samples are the same across different classes. Unfortunately, in practice, such an assumption does not always hold due to the varying learning difficulty of different classes, thus leading to sub-optimal label noise partition criteria. In this work, we reveal this long-ignored problem and propose a simple yet effective solution, named \textbf{C}lass \textbf{P}rototype-based label noise \textbf{C}leaner (\textbf{CPC}). Unlike previous works treating all the classes equally, CPC fully considers loss distribution heterogeneity and applies class-aware modulation to partition the clean and noise data. CPC takes advantage of loss distribution modeling and intra-class consistency regularization in feature space simultaneously and thus can better distinguish clean and noise labels. We theoretically justify the effectiveness of our method by explaining it from the Expectation-Maximization (EM) framework. Extensive experiments are conducted on the noisy-label benchmarks CIFAR-10, CIFAR-100, Clothing1M and WebVision. The results show that CPC consistently brings about performance improvement across all benchmarks. Codes and pre-trained models will be released at \url{https://github.com/hjjpku/CPC.git}.
translated by 谷歌翻译