标签噪声在大型现实世界数据集中很常见，其存在会损害深神网络的训练过程。尽管几项工作集中在解决此问题的培训策略上，但很少有研究评估数据增强作为培训深神经网络的设计选择。在这项工作中，我们分析了使用不同数据增强的模型鲁棒性及其在嘈杂标签的存在下对培训的改进。我们评估了数据集MNIST，CIFAR-10，CIFAR-100和现实世界数据集Clothing1M的最新和经典数据增强策略，具有不同级别的合成噪声。我们使用精度度量评估方法。结果表明，与基线相比，适当的数据增强可以大大提高模型的稳健性，可将相对最佳测试准确性的177.84％提高到177.84％的相对最佳测试准确性，而无需增强，并且随着绝对值增加了6％，而该基线的绝对值增加了6％最先进的Dividemix培训策略。

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。

Convolutional Neural Networks (CNNs) have demonstrated superiority in learning patterns, but are sensitive to label noises and may overfit noisy labels during training. The early stopping strategy averts updating CNNs during the early training phase and is widely employed in the presence of noisy labels. Motivated by biological findings that the amplitude spectrum (AS) and phase spectrum (PS) in the frequency domain play different roles in the animal's vision system, we observe that PS, which captures more semantic information, can increase the robustness of DNNs to label noise, more so than AS can. We thus propose early stops at different times for AS and PS by disentangling the features of some layer(s) into AS and PS using Discrete Fourier Transform (DFT) during training. Our proposed Phase-AmplituDe DisentangLed Early Stopping (PADDLES) method is shown to be effective on both synthetic and real-world label-noise datasets. PADDLES outperforms other early stopping methods and obtains state-of-the-art performance.

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.

Despite being robust to small amounts of label noise, convolutional neural networks trained with stochastic gradient methods have been shown to easily fit random labels. When there are a mixture of correct and mislabelled targets, networks tend to fit the former before the latter. This suggests using a suitable two-component mixture model as an unsupervised generative model of sample loss values during training to allow online estimation of the probability that a sample is mislabelled. Specifically, we propose a beta mixture to estimate this probability and correct the loss by relying on the network prediction (the so-called bootstrapping loss). We further adapt mixup augmentation to drive our approach a step further. Experiments on CIFAR-10/100 and TinyImageNet demonstrate a robustness to label noise that substantially outperforms recent state-of-the-art. Source code is available at https://git.io/fjsvE.

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。

Transfer of pre-trained representations improves sample efficiency and simplifies hyperparameter tuning when training deep neural networks for vision. We revisit the paradigm of pre-training on large supervised datasets and fine-tuning the model on a target task. We scale up pre-training, and propose a simple recipe that we call Big Transfer (BiT). By combining a few carefully selected components, and transferring using a simple heuristic, we achieve strong performance on over 20 datasets. BiT performs well across a surprisingly wide range of data regimes -from 1 example per class to 1 M total examples. BiT achieves 87.5% top-1 accuracy on ILSVRC-2012, 99.4% on CIFAR-10, and 76.3% on the 19 task Visual Task Adaptation Benchmark (VTAB). On small datasets, BiT attains 76.8% on ILSVRC-2012 with 10 examples per class, and 97.0% on CIFAR-10 with 10 examples per class. We conduct detailed analysis of the main components that lead to high transfer performance.

嘈杂的标签损坏了深网络的性能。为了稳健的学习，突出的两级管道在消除可能的不正确标签和半监督培训之间交替。然而，丢弃观察到的标签的部分可能导致信息丢失，尤其是当腐败不是完全随机的时，例如依赖类或实例依赖。此外，从代表性两级方法Dividemix的训练动态，我们确定了确认偏置的统治：伪标签未能纠正相当大量的嘈杂标签，因此累积误差。为了充分利用观察到的标签和减轻错误的校正，我们提出了强大的标签翻新（鲁棒LR）-a新的混合方法，该方法集成了伪标签和置信度估计技术来翻新嘈杂的标签。我们表明我们的方法成功减轻了标签噪声和确认偏差的损害。结果，它跨数据集和噪声类型实现最先进的结果。例如，强大的LR在真实世界嘈杂的数据集网络VIVION上以前最好的绝对高度提高了4.5％的绝对顶级精度改进。

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。

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.

我们向您展示一次（YOCO）进行数据增强。 Yoco将一张图像切成两片，并在每件零件中单独执行数据增强。应用YOCO改善了每个样品的增强的多样性，并鼓励神经网络从部分信息中识别对象。 Yoco享受无参数，轻松使用的属性，并免费提供几乎所有的增强功能。进行了彻底的实验以评估其有效性。我们首先证明Yoco可以无缝地应用于不同的数据增强，神经网络体系结构，并在CIFAR和Imagenet分类任务上带来性能提高，有时会超过传统的图像级增强。此外，我们显示了Yoco益处对比的预培训，以更强大的表示，可以更好地转移到多个下游任务。最后，我们研究了Yoco的许多变体，并经验分析了各个设置的性能。代码可在GitHub上找到。

In this paper, we introduced the novel concept of advisor network to address the problem of noisy labels in image classification. Deep neural networks (DNN) are prone to performance reduction and overfitting problems on training data with noisy annotations. Weighting loss methods aim to mitigate the influence of noisy labels during the training, completely removing their contribution. This discarding process prevents DNNs from learning wrong associations between images and their correct labels but reduces the amount of data used, especially when most of the samples have noisy labels. Differently, our method weighs the feature extracted directly from the classifier without altering the loss value of each data. The advisor helps to focus only on some part of the information present in mislabeled examples, allowing the classifier to leverage that data as well. We trained it with a meta-learning strategy so that it can adapt throughout the training of the main model. We tested our method on CIFAR10 and CIFAR100 with synthetic noise, and on Clothing1M which contains real-world noise, reporting state-of-the-art results.

Semi-supervised learning (SSL) provides an effective means of leveraging unlabeled data to improve a model's performance. This domain has seen fast progress recently, at the cost of requiring more complex methods. In this paper we propose FixMatch, an algorithm that is a significant simplification of existing SSL methods. FixMatch first generates pseudo-labels using the model's predictions on weaklyaugmented unlabeled images. For a given image, the pseudo-label is only retained if the model produces a high-confidence prediction. The model is then trained to predict the pseudo-label when fed a strongly-augmented version of the same image. Despite its simplicity, we show that FixMatch achieves state-of-the-art performance across a variety of standard semi-supervised learning benchmarks, including 94.93% accuracy on CIFAR-10 with 250 labels and 88.61% accuracy with 40 -just 4 labels per class. We carry out an extensive ablation study to tease apart the experimental factors that are most important to FixMatch's success. The code is available at https://github.com/google-research/fixmatch.

使用卷积神经网络（CNN）已经显着改善了几种图像处理任务，例如图像分类和对象检测。与Reset和Abseralnet一样，许多架构在创建时至少在一个数据集中实现了出色的结果。培训的一个关键因素涉及网络的正规化，这可以防止结构过度装备。这项工作分析了在过去几年中开发的几种正规化方法，显示了不同CNN模型的显着改进。该作品分为三个主要区域：第一个称为“数据增强”，其中所有技术都侧重于执行输入数据的更改。第二个，命名为“内部更改”，旨在描述修改神经网络或内核生成的特征映射的过程。最后一个称为“标签”，涉及转换给定输入的标签。这项工作提出了与关于正则化的其他可用调查相比的两个主要差异：（i）第一个涉及在稿件中收集的论文并非超过五年，并第二个区别是关于可重复性，即所有作品此处推荐在公共存储库中可用的代码，或者它们已直接在某些框架中实现，例如Tensorflow或Torch。

在许多分类问题中，我们希望一个对一系列非语义转换具有强大的分类器。例如，无论其出现的方向和姿势如何，人都可以识别图片中的狗。存在实质性证据表明这种不变性可以显着提高机器学习模型的准确性和泛化。教导模型几何修正型的常用技术是通过变换输入来增加训练数据。但是，对于给定的分类任务期望需要哪种修正，并不总是已知的。确定有效的数据增强策略可以要求域专业知识或广泛的数据预处理。最近的努力，如自动化优化数据增强策略的参数化搜索空间，以自动化增强过程。虽然自动化和类似方法在几个常见的数据集上实现最先进的分类准确性，但它们仅限于学习一个数据增强策略。通常不同的类别或功能呼叫不同的几何修正。我们介绍了动态网络增强（DNA），从而了解输入条件增强策略。我们模型中的增强参数是神经网络的输出，并且随着网络权重被更新时被隐式学习。我们的模型允许动态增强策略，并在输入功能上具有几何变换的数据良好。

不完美的标签在现实世界数据集中无处不在，严重损害了模型性能。几个最近处理嘈杂标签的有效方法有两个关键步骤：1）将样品分开通过培训丢失，2）使用半监控方法在错误标记的集合中生成样本的伪标签。然而，由于硬样品和噪声之间的类似损失分布，目前的方法总是损害信息性的硬样品。在本文中，我们提出了PGDF（先前引导的去噪框架），通过生成样本的先验知识来学习深层模型来抑制噪声的新框架，这被集成到分割样本步骤和半监督步骤中。我们的框架可以将更多信息性硬清洁样本保存到干净标记的集合中。此外，我们的框架还通过抑制当前伪标签生成方案中的噪声来促进半监控步骤期间伪标签的质量。为了进一步增强硬样品，我们在训练期间在干净的标记集合中重新重量样品。我们使用基于CiFar-10和CiFar-100的合成数据集以及现实世界数据集WebVision和服装1M进行了评估了我们的方法。结果表明了最先进的方法的大量改进。

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。

Data augmentation is an effective technique for improving the accuracy of modern image classifiers. However, current data augmentation implementations are manually designed. In this paper, we describe a simple procedure called AutoAugment to automatically search for improved data augmentation policies. In our implementation, we have designed a search space where a policy consists of many subpolicies, one of which is randomly chosen for each image in each mini-batch. A sub-policy consists of two operations, each operation being an image processing function such as translation, rotation, or shearing, and the probabilities and magnitudes with which the functions are applied. We use a search algorithm to find the best policy such that the neural network yields the highest validation accuracy on a target dataset. Our method achieves state-of-the-art accuracy on SVHN, and ImageNet (without additional data). On ImageNet, we attain a Top-1 accuracy of 83.5% which is 0.4% better than the previous record of 83.1%. On CIFAR-10, we achieve an error rate of 1.5%, which is 0.6% better than the previous state-of-theart. Augmentation policies we find are transferable between datasets. The policy learned on ImageNet transfers well to achieve significant improvements on other datasets, such as Oxford Flowers, Caltech-101, Oxford-IIT Pets, FGVC Aircraft, and Stanford Cars. * Work performed as a member of the Google Brain Residency Program.† Equal contribution.

对抗性训练遭受了稳健的过度装备，这是一种现象，在训练期间鲁棒测试精度开始减少。在本文中，我们专注于通过使用常见的数据增强方案来减少强大的过度装备。我们证明，与先前的发现相反，当与模型重量平均结合时，数据增强可以显着提高鲁棒精度。此外，我们比较各种增强技术，并观察到空间组合技术适用于对抗性培训。最后，我们评估了我们在Cifar-10上的方法，而不是$ \ ell_ indty $和$ \ ell_2 $ norm-indeded扰动分别为尺寸$ \ epsilon = 8/255 $和$ \ epsilon = 128/255 $。与以前的最先进的方法相比，我们表现出+ 2.93％的绝对改善+ 2.93％，+ 2.16％。特别是，反对$ \ ell_ infty $ norm-indeded扰动尺寸$ \ epsilon = 8/255 $，我们的模型达到60.07％的强劲准确性而不使用任何外部数据。我们还通过这种方法实现了显着的性能提升，同时使用其他架构和数据集如CiFar-100，SVHN和TinyimageNet。

数据增强方法丰富具有增强数据的数据集以提高神经网络的性能。最近，已经出现了自动化数据增强方法，自动设计增强策略。现有工作侧重于图像分类和对象检测，而我们提供了关于语义图像分割的第一次研究，并引入了两种新方法：\ Textit {Smartaugment}和\ Textit {SmartSamplingAugment}。 Smartaugment使用贝叶斯优化来搜索增强策略的丰富空间，并在我们考虑的所有语义细分任务中实现了新的最先进的性能。 SmartSamplingAugment，一种具有固定增强策略的简单参数方法，可与现有的资源密集型方法竞争性能，并且优于廉价的最先进的数据增强方法。此外，我们分析了数据增强超参数的影响，互动和重要性，并进行了融合研究，这确认了我们的设计选择，背后是Smartaugment和SmartSamplingAugment。最后，我们将提供我们的源代码以进行再现性，并促进进一步的研究。