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
Deep models for facial expression recognition achieve high performance by training on large-scale labeled data. However, publicly available datasets contain uncertain facial expressions caused by ambiguous annotations or confusing emotions, which could severely decline the robustness. Previous studies usually follow the bias elimination method in general tasks without considering the uncertainty problem from the perspective of different corresponding sources. In this paper, we propose a novel method of multi-task assisted correction in addressing uncertain facial expression recognition called MTAC. Specifically, a confidence estimation block and a weighted regularization module are applied to highlight solid samples and suppress uncertain samples in every batch. In addition, two auxiliary tasks, i.e., action unit detection and valence-arousal measurement, are introduced to learn semantic distributions from a data-driven AU graph and mitigate category imbalance based on latent dependencies between discrete and continuous emotions, respectively. Moreover, a re-labeling strategy guided by feature-level similarity constraint further generates new labels for identified uncertain samples to promote model learning. The proposed method can flexibly combine with existing frameworks in a fully-supervised or weakly-supervised manner. Experiments on RAF-DB, AffectNet, and AffWild2 datasets demonstrate that the MTAC obtains substantial improvements over baselines when facing synthetic and real uncertainties and outperforms the state-of-the-art methods.
translated by 谷歌翻译
由于类间的相似性和注释歧义,嘈杂的标签面部表达识别(FER)比传统的嘈杂标签分类任务更具挑战性。最近的作品主要通过过滤大量损坏样本来解决此问题。在本文中,我们从新功能学习的角度探索了嘈杂的标签。我们发现,FER模型通过专注于可以认为与嘈杂标签相关的一部分来记住嘈杂的样本,而不是从导致潜在真理的整个功能中学习。受到的启发,我们提出了一种新颖的擦除注意力一致性(EAC)方法,以自动抑制嘈杂的样品。具体而言,我们首先利用面部图像的翻转语义一致性来设计不平衡的框架。然后,我们随机删除输入图像,并使用翻转注意一致性,以防止模型专注于部分特征。 EAC明显优于最先进的嘈杂标签方法,并将其概括地概括为其他类似CIFAR100和Tiny-Imagenet等类别的任务。该代码可在https://github.com/zyh-uaiaaaa/erasing-prestention-consistency中获得。
translated by 谷歌翻译
尽管在过去的几年中取得了重大进展,但歧义仍然是面部表情识别(FER)的关键挑战。它可能导致嘈杂和不一致的注释,这阻碍了现实世界中深度学习模型的性能。在本文中,我们提出了一种新的不确定性标签分布学习方法,以提高深层模型的鲁棒性,以防止不确定性和歧义。我们利用价值空间中的邻里信息来适应培训训练样本的情绪分布。我们还考虑提供的标签将其纳入标签分布时的不确定性。我们的方法可以轻松地集成到深层网络中,以获得更多的培训监督并提高识别准确性。在各种嘈杂和模棱两可的环境下,在几个数据集上进行了密集的实验表明,我们的方法取得了竞争成果,并且超出了最新的最新方法。我们的代码和模型可在https://github.com/minhnhatvt/label-distribution-learning-fer-tf上找到。
translated by 谷歌翻译
Deep Learning with noisy labels is a practically challenging problem in weakly supervised learning. The stateof-the-art approaches "Decoupling" and "Co-teaching+" claim that the "disagreement" strategy is crucial for alleviating the problem of learning with noisy labels. In this paper, we start from a different perspective and propose a robust learning paradigm called JoCoR, which aims to reduce the diversity of two networks during training. Specifically, we first use two networks to make predictions on the same mini-batch data and calculate a joint loss with Co-Regularization for each training example. Then we select small-loss examples to update the parameters of both two networks simultaneously. Trained by the joint loss, these two networks would be more and more similar due to the effect of Co-Regularization. Extensive experimental results on corrupted data from benchmark datasets including MNIST, CIFAR-10, CIFAR-100 and Clothing1M demonstrate that JoCoR is superior to many state-of-the-art approaches for learning with noisy labels.
translated by 谷歌翻译
应付嘈杂标签的大多数现有方法通常假定类别分布良好,因此无法应对训练样本不平衡分布的实际情况的能力不足。为此,本文尽早努力通过长尾分配和标签噪声来解决图像分类任务。在这种情况下,现有的噪声学习方法无法正常工作,因为将噪声样本与干净的尾巴类别的样本区分开来是具有挑战性的。为了解决这个问题,我们提出了一个新的学习范式,基于对弱数据和强数据扩展的推论,以筛选嘈杂的样本,并引入休假散布的正则化,以消除公认的嘈杂样本的效果。此外,我们基于在线先验分布中纳入了一种新颖的预测惩罚,以避免对头等阶层的偏见。与现有的长尾分类方法相比,这种机制在实时捕获班级拟合度方面具有优越性。详尽的实验表明,所提出的方法优于解决噪声标签下长尾分类中分布不平衡问题的最先进算法。
translated by 谷歌翻译
自动情感识别在许多领域都有应用,例如教育,游戏,软件开发,汽车,医疗保健等。但是,在野外数据集上实现可观的绩效是无琐的任务。野外数据集虽然比合成数据集更好地代表了现实世界中的情况,但前者遇到了不完整标签的问题。受到半监督学习的启发,在本文中,我们在第四次情感行为分析(ABAW)2022竞赛中介绍了提交的多任务学习挑战。在这项挑战中考虑的三个任务是价估计(VA)估计,表达式分为6个基本(愤怒,厌恶,恐惧,幸福,悲伤,惊喜),中立和“其他”类别和12个行动单位(au)编号au - \ {1,2,4,6,7,10,12,15,15,23,24,25,26 \}。我们的方法半监督的多任务面部情感情感识别标题为\ textbf {ss-mfar}使用一个深层残留网络,每个任务都具有特定任务分类器以及每个表达式类别的自适应阈值,每个表达式类别和半监督学习。源代码可从https://github.com/1980x/abaw202​​22dmacs获得。
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
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
对标签噪声的学习是一个至关重要的话题,可以保证深度神经网络的可靠表现。最近的研究通常是指具有模型输出概率和损失值的动态噪声建模,然后分离清洁和嘈杂的样本。这些方法取得了显着的成功。但是,与樱桃挑选的数据不同,现有方法在面对不平衡数据集时通常无法表现良好,这是现实世界中常见的情况。我们彻底研究了这一现象,并指出了两个主要问题,这些问题阻碍了性能,即\ emph {类间损耗分布差异}和\ emph {由于不确定性而引起的误导性预测}。第一个问题是现有方法通常执行类不足的噪声建模。然而,损失分布显示在类失衡下的类别之间存在显着差异,并且类不足的噪声建模很容易与少数族裔类别中的嘈杂样本和样本混淆。第二个问题是指该模型可能会因认知不确定性和不确定性而导致的误导性预测,因此仅依靠输出概率的现有方法可能无法区分自信的样本。受我们的观察启发,我们提出了一个不确定性的标签校正框架〜(ULC)来处理不平衡数据集上的标签噪声。首先,我们执行认识不确定性的班级特异性噪声建模,以识别可信赖的干净样本并精炼/丢弃高度自信的真实/损坏的标签。然后,我们在随后的学习过程中介绍了不确定性,以防止标签噪声建模过程中的噪声积累。我们对几个合成和现实世界数据集进行实验。结果证明了提出的方法的有效性,尤其是在数据集中。
translated by 谷歌翻译
High-quality annotated images are significant to deep facial expression recognition (FER) methods. However, uncertain labels, mostly existing in large-scale public datasets, often mislead the training process. In this paper, we achieve uncertain label correction of facial expressions using auxiliary action unit (AU) graphs, called ULC-AG. Specifically, a weighted regularization module is introduced to highlight valid samples and suppress category imbalance in every batch. Based on the latent dependency between emotions and AUs, an auxiliary branch using graph convolutional layers is added to extract the semantic information from graph topologies. Finally, a re-labeling strategy corrects the ambiguous annotations by comparing their feature similarities with semantic templates. Experiments show that our ULC-AG achieves 89.31% and 61.57% accuracy on RAF-DB and AffectNet datasets, respectively, outperforming the baseline and state-of-the-art methods.
translated by 谷歌翻译
We approach the problem of improving robustness of deep learning algorithms in the presence of label noise. Building upon existing label correction and co-teaching methods, we propose a novel training procedure to mitigate the memorization of noisy labels, called CrossSplit, which uses a pair of neural networks trained on two disjoint parts of the dataset. CrossSplit combines two main ingredients: (i) Cross-split label correction. The idea is that, since the model trained on one part of the data cannot memorize example-label pairs from the other part, the training labels presented to each network can be smoothly adjusted by using the predictions of its peer network; (ii) Cross-split semi-supervised training. A network trained on one part of the data also uses the unlabeled inputs of the other part. Extensive experiments on CIFAR-10, CIFAR-100, Tiny-ImageNet and mini-WebVision datasets demonstrate that our method can outperform the current state-of-the-art up to 90% noise ratio.
translated by 谷歌翻译
样品选择是减轻标签噪声在鲁棒学习中的影响的有效策略。典型的策略通常应用小损失标准来识别干净的样品。但是,这些样本位于决策边界周围,通常会与嘈杂的例子纠缠在一起,这将被此标准丢弃,从而导致概括性能的严重退化。在本文中,我们提出了一种新颖的选择策略,\ textbf {s} elf- \ textbf {f} il \ textbf {t} ering(sft),它利用历史预测中嘈杂的示例的波动来过滤它们,可以过滤它们,这可以是可以过滤的。避免在边界示例中的小损失标准的选择偏置。具体来说,我们介绍了一个存储库模块,该模块存储了每个示例的历史预测,并动态更新以支持随后的学习迭代的选择。此外,为了减少SFT样本选择偏置的累积误差,我们设计了一个正规化术语来惩罚自信的输出分布。通过通过此术语增加错误分类类别的重量,损失函数在轻度条件下标记噪声是可靠的。我们对具有变化噪声类型的三个基准测试并实现了新的最先进的实验。消融研究和进一步分析验证了SFT在健壮学习中选择样本的优点。
translated by 谷歌翻译
常规的去命名方法依赖于所有样品都是独立且分布相同的假设,因此最终的分类器虽然受到噪声的干扰,但仍然可以轻松地将噪声识别为训练分布的异常值。但是,在不可避免地长尾巴的大规模数据中,该假设是不现实的。这种不平衡的训练数据使分类器对尾巴类别的歧视性较小,而尾巴类别的差异化现在变成了“硬”的噪声 - 它们几乎与干净的尾巴样品一样离群值。我们将这一新挑战介绍为嘈杂的长尾分类(NLT)。毫不奇怪,我们发现大多数拖延方法无法识别出硬噪声,从而导致三个提出的NLT基准测试的性能大幅下降:Imagenet-NLT,Animal10-NLT和Food101-NLT。为此,我们设计了一个迭代嘈杂的学习框架,称为“难以容易”(H2E)。我们的引导理念是首先学习一个分类器作为噪声标识符不变的类和上下文分布变化,从而将“硬”噪声减少到“ Easy”的噪声,其删除进一步改善了不变性。实验结果表明,我们的H2E胜过最先进的方法及其在长尾设置上的消融,同时在传统平衡设置上保持稳定的性能。数据集和代码可从https://github.com/yxymessi/h2e-framework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
使用嘈杂标签(LNL)学习旨在设计策略来通过减轻模型过度适应嘈杂标签的影响来提高模型性能和概括。 LNL的主要成功在于从大量嘈杂数据中识别尽可能多的干净样品,同时纠正错误分配的嘈杂标签。最近的进步采用了单个样品的预测标签分布来执行噪声验证和嘈杂的标签校正,很容易产生确认偏差。为了减轻此问题,我们提出了邻里集体估计,其中通过将其与其功能空间最近的邻居进行对比,重新估计了候选样本的预测性可靠性。具体而言,我们的方法分为两个步骤:1)邻域集体噪声验证,将所有训练样品分为干净或嘈杂的子集,2)邻里集体标签校正到Relabel嘈杂样品,然后使用辅助技术来帮助进一步的模型优化。 。在四个常用基准数据集(即CIFAR-10,CIFAR-100,Clothing-1M和WebVision-1.0)上进行了广泛的实验,这表明我们提出的方法非常优于最先进的方法。
translated by 谷歌翻译
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
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
Learning with noisy labels is a vital topic for practical deep learning as models should be robust to noisy open-world datasets in the wild. The state-of-the-art noisy label learning approach JoCoR fails when faced with a large ratio of noisy labels. Moreover, selecting small-loss samples can also cause error accumulation as once the noisy samples are mistakenly selected as small-loss samples, they are more likely to be selected again. In this paper, we try to deal with error accumulation in noisy label learning from both model and data perspectives. We introduce mean point ensemble to utilize a more robust loss function and more information from unselected samples to reduce error accumulation from the model perspective. Furthermore, as the flip images have the same semantic meaning as the original images, we select small-loss samples according to the loss values of flip images instead of the original ones to reduce error accumulation from the data perspective. Extensive experiments on CIFAR-10, CIFAR-100, and large-scale Clothing1M show that our method outperforms state-of-the-art noisy label learning methods with different levels of label noise. Our method can also be seamlessly combined with other noisy label learning methods to further improve their performance and generalize well to other tasks. The code is available in https://github.com/zyh-uaiaaaa/MDA-noisy-label-learning.
translated by 谷歌翻译
深度学习在许多领域取得了许多显着的成就,但数据集中有嘈杂的标签。使用嘈杂的标签方法共同教学和共同教学的最先进的学习+通过双网络之间的相互信息面对嘈杂的标签。但是,双网络始终倾向于收敛,这会削弱双网机制以抵抗嘈杂标签。在本文中,我们以端到端的方式提出了一个名为MLC的耐噪声框架。它通过不同的正则化来调整双网络,以确保机制的有效性。此外,我们根据双网络之间的协议纠正标签分布。提出的方法可以利用嘈杂的数据来提高网络的准确性,概括和鲁棒性。我们在模拟嘈杂的数据集MNIST,CIFAR-10和现实世界嘈杂的数据集服装上测试了提出的方法。1M。实验结果表明,我们的方法优于先前的最新方法。此外,我们的方法是无网络的,因此它适用于许多任务。我们的代码可以在https://github.com/jiarunliu/mlc上找到。
translated by 谷歌翻译