In semi-supervised representation learning frameworks, when the number of labelled data is very scarce, the quality and representativeness of these samples become increasingly important. Existing literature on semi-supervised learning randomly sample a limited number of data points for labelling. All these labelled samples are then used along with the unlabelled data throughout the training process. In this work, we ask two important questions in this context: (1) does it matter which samples are selected for labelling? (2) does it matter how the labelled samples are used throughout the training process along with the unlabelled data? To answer the first question, we explore a number of unsupervised methods for selecting specific subsets of data to label (without prior knowledge of their labels), with the goal of maximizing representativeness w.r.t. the unlabelled set. Then, for our second line of inquiry, we define a variety of different label injection strategies in the training process. Extensive experiments on four popular datasets, CIFAR-10, CIFAR-100, SVHN, and STL-10, show that unsupervised selection of samples that are more representative of the entire data improves performance by up to ~2% over the existing semi-supervised frameworks such as MixMatch, ReMixMatch, FixMatch and others with random sample labelling. We show that this boost could even increase to 7.5% for very few-labelled scenarios. However, our study shows that gradually injecting the labels throughout the training procedure does not impact the performance considerably versus when all the existing labels are used throughout the entire training.
translated by 谷歌翻译
培训深层神经网络以识别图像识别通常需要大规模的人类注释数据。为了减少深神经溶液对标记数据的依赖,文献中已经提出了最先进的半监督方法。尽管如此,在面部表达识别领域(FER)领域,使用这种半监督方法非常罕见。在本文中,我们介绍了一项关于最近提出的在FER背景下的最先进的半监督学习方法的全面研究。我们对八种半监督学习方法进行了比较研究当使用各种标记的样品时。我们还将这些方法的性能与完全监督的培训进行了比较。我们的研究表明,当培训现有的半监督方法时,每类标记的样本只有250个标记的样品可以产生可比的性能,而在完整标记的数据集中训练的完全监督的方法。为了促进该领域的进一步研究,我们在:https://github.com/shuvenduroy/ssl_fer上公开提供代码
translated by 谷歌翻译
半监督的学习受到了最近的关注,因为它减轻了对大量标签数据的需求,这些数据通常很昂贵,需要专家知识并耗时收集。深度半监督分类的最新发展已经达到了前所未有的表现,而受监督和半监督学习之间的差距一直在挑战。这种绩效的改善是基于包含众多技术技巧,强大的增强技术和具有多项损失功能的昂贵优化方案。我们提出了一个新的框架,即laplacenet,以进行深度半监督分类,该分类大大降低了模型的复杂性。我们利用一种混合方法,在该方法中,通过将图表上的laplacian能量最小化来产生伪标记。然后,这些伪标签被用来迭代训练神经网络骨架。在几个基准数据集上,我们的模型优于深度半监督分类的最先进方法。此外,我们在理论上考虑了强大化对神经网络的应用,并证明使用多样采样方法对半监督学习的使用是合理的。我们通过严格的实验证明,多样采样增强方法可以改善概括并降低网络对增强的敏感性。
translated by 谷歌翻译
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.
translated by 谷歌翻译
长期以来,半监督学习(SSL)已被证明是一种有限的标签模型的有效技术。在现有的文献中,基于一致性的基于正则化的方法,这些方法迫使扰动样本具有类似的预测,而原始的样本则引起了极大的关注。但是,我们观察到,当标签变得极为有限时,例如,每个类别的2或3标签时,此类方法的性能会大大降低。我们的实证研究发现,主要问题在于语义信息在数据增强过程中的漂移。当提供足够的监督时,可以缓解问题。但是,如果几乎没有指导,错误的正则化将误导网络并破坏算法的性能。为了解决该问题,我们(1)提出了一种基于插值的方法来构建更可靠的正样品对; (2)设计一种新颖的对比损失,以指导学习网络的嵌入以在样品之间进行线性更改,从而通过扩大保证金决策边界来提高网络的歧视能力。由于未引入破坏性正则化,因此我们提出的算法的性能在很大程度上得到了改善。具体而言,所提出的算法的表现优于第二好算法(COMATT),而当CIFAR-10数据集中的每个类只有两个标签可用时,可以实现88.73%的分类精度,占5.3%。此外,我们通过通过我们提出的策略大大改善现有最新算法的性能,进一步证明了所提出的方法的普遍性。
translated by 谷歌翻译
鉴于获得大量标记数据的潜在困难,许多作品探索了使用深度半监督学习,它使用标记和未标记的数据来培训神经网络架构。绝大多数SSL方法侧重于实现低密度分离假设或一致性假设,决策边界应该位于低密度区域的想法。但是,它们通过对每个数据点的决策边界进行本地更改来实现这一假设,忽略了数据的全局结构。在这项工作中,我们使用群集数据中存在的全局信息来探索替代方法来更新我们的决策边界。我们提出了一种新颖的框架,Cyclecluster,用于深度半监督分类。我们的核心优化由基于新的聚类正则化以及基于图形的伪标签和共享的深网络的基于群集的正规化驱动。展示集群假设的直接实现是基于流行的一致性正规化的可行替代方案。我们通过仔细的数值结果展示了我们技术的预测能力。
translated by 谷歌翻译
一个常见的分类任务情况是,有大量数据可用于培训,但只有一小部分用类标签注释。在这种情况下,半监督培训的目的是通过利用标记数据,而且从大量未标记的数据中提高分类准确性。最近的作品通过探索不同标记和未标记数据的不同增强性数据之间的一致性约束,从而取得了重大改进。遵循这条路径,我们提出了一个新颖的无监督目标,该目标侧重于彼此相似的高置信度未标记的数据之间所研究的关系较少。新提出的对损失最大程度地减少了高置信度伪伪标签之间的统计距离,其相似性高于一定阈值。我们提出的简单算法将对损失与MixMatch家族开发的技术结合在一起,显示出比以前在CIFAR-100和MINI-IMAGENET上的算法的显着性能增长,并且与CIFAR-的最先进方法相当。 10和SVHN。此外,简单还优于传输学习设置中最新方法,其中模型是由在ImainEnet或域内实现的权重初始化的。该代码可在github.com/zijian-hu/simple上获得。
translated by 谷歌翻译
This work tackles the problem of semi-supervised learning of image classifiers. Our main insight is that the field of semi-supervised learning can benefit from the quickly advancing field of self-supervised visual representation learning. Unifying these two approaches, we propose the framework of self-supervised semi-supervised learning (S 4 L) and use it to derive two novel semi-supervised image classification methods. We demonstrate the effectiveness of these methods in comparison to both carefully tuned baselines, and existing semi-supervised learning methods. We then show that S 4 L and existing semi-supervised methods can be jointly trained, yielding a new state-of-the-art result on semi-supervised ILSVRC-2012 with 10% of labels.
translated by 谷歌翻译
标签预测上的一致性正则化成为半监督学习中的一项基本技术,但是它仍然需要大量的训练迭代以进行高性能。在这项研究中,我们分析了一致性正则化限制了由于在模型更新中排除具有不受欢迎的伪标记的样品,因此标记信息的传播限制了。然后,我们提出对比度正则化,以提高未标记数据的群集特征一致性正则化的效率和准确性。在特定的情况下,在通过其伪标签将强大的增强样品分配给群集后,我们的对比度正规化更新了模型,以便具有自信的伪标签的功能在同一集群中汇总了功能,同时将功能推迟了不同的群集中的功能。结果,在培训中,可以有效地将自信的伪标签的信息有效地传播到更无标记的样品中。在半监督学习任务的基准上,我们的对比正则化改善了以前的基于一致性的方法,并取得了最新的结果,尤其是在培训次数较少的情况下。我们的方法还显示了在开放式半监督学习中的稳健性能,其中未标记的数据包括分发样本。
translated by 谷歌翻译
我们研究了用于半监控学习(SSL)的无监督数据选择,其中可以提供大规模的未标记数据集,并且为标签采集预算小额数据子集。现有的SSL方法专注于学习一个有效地集成了来自给定小标记数据和大型未标记数据的信息的模型,而我们专注于选择正确的数据以用于SSL的注释,而无需任何标签或任务信息。直观地,要标记的实例应统称为下游任务的最大多样性和覆盖范围,并且单独具有用于SSL的最大信息传播实用程序。我们以三步数据为中心的SSL方法形式化这些概念,使稳定性和精度的纤维液改善8%的CiFar-10(标记为0.08%)和14%的Imagenet -1k(标记为0.2%)。它也是一种具有各种SSL方法的通用框架,提供一致的性能增益。我们的工作表明,在仔细选择注释数据上花费的小计算带来了大注释效率和模型性能增益,而无需改变学习管道。我们完全无监督的数据选择可以轻松扩展到其他弱监督的学习设置。
translated by 谷歌翻译
The core issue in semi-supervised learning (SSL) lies in how to effectively leverage unlabeled data, whereas most existing methods tend to put a great emphasis on the utilization of high-confidence samples yet seldom fully explore the usage of low-confidence samples. In this paper, we aim to utilize low-confidence samples in a novel way with our proposed mutex-based consistency regularization, namely MutexMatch. Specifically, the high-confidence samples are required to exactly predict "what it is" by conventional True-Positive Classifier, while the low-confidence samples are employed to achieve a simpler goal -- to predict with ease "what it is not" by True-Negative Classifier. In this sense, we not only mitigate the pseudo-labeling errors but also make full use of the low-confidence unlabeled data by consistency of dissimilarity degree. MutexMatch achieves superior performance on multiple benchmark datasets, i.e., CIFAR-10, CIFAR-100, SVHN, STL-10, mini-ImageNet and Tiny-ImageNet. More importantly, our method further shows superiority when the amount of labeled data is scarce, e.g., 92.23% accuracy with only 20 labeled data on CIFAR-10. Our code and model weights have been released at https://github.com/NJUyued/MutexMatch4SSL.
translated by 谷歌翻译
Semi-supervised learning has proven to be a powerful paradigm for leveraging unlabeled data to mitigate the reliance on large labeled datasets. In this work, we unify the current dominant approaches for semi-supervised learning to produce a new algorithm, MixMatch, that guesses low-entropy labels for data-augmented unlabeled examples and mixes labeled and unlabeled data using MixUp. MixMatch obtains state-of-the-art results by a large margin across many datasets and labeled data amounts. For example, on CIFAR-10 with 250 labels, we reduce error rate by a factor of 4 (from 38% to 11%) and by a factor of 2 on STL-10. We also demonstrate how MixMatch can help achieve a dramatically better accuracy-privacy trade-off for differential privacy. Finally, we perform an ablation study to tease apart which components of MixMatch are most important for its success. We release all code used in our experiments. 1
translated by 谷歌翻译
半监督学习方法已成为对打击获得大量注释数据的挑战的活跃研究领域。为了提高半监督学习方法表现的目标,我们提出了一种新颖的框架,Hiematch,一种半监督方法,利用分层信息来降低标签成本并表现以及vanilla半监督学习方法。分层信息通常是具有细粒标签的粗标签(例如,啄木鸟)的粗标签(例如,啄木鸟)的现有知识(例如,柔软的啄木鸟或金朝啄木鸟)。但是,尚未探讨使用使用粗类标签来改进半监督技术的监督。在没有细粒度的标签的情况下,Himatch利用标签层次结构,并使用粗级标签作为弱监控信号。此外,Himatch是一种改进任何半熟的学习框架的通用方法,我们使用我们的结果在最近的最先进的技术Mixmatch和Fixmatch上展示了这一点。我们评估了在两个基准数据集,即CiFar-100和Nabirds上的Himatch疗效。与MixMatch相比,HOMACHACT可以在CIFAR-100上减少50%的粒度标签50%的用量,仅在前1个精度的边缘下降0.59%。代码:https://github.com/07agarg/hiermatch.
translated by 谷歌翻译
大型标记数据集的可用性是深度学习成功的关键组成部分。但是,大型数据集上的标签通常很耗时且昂贵。主动学习是一个研究领域,通过选择最重要的标签样本来解决昂贵的标签问题。基于多样性的采样算法被称为基于表示的主动学习方法的组成部分。在本文中,我们介绍了一种新的基于多样性的初始数据集选择算法,以选择有效学习环境中初始标记的最有用的样本集。自我监督的表示学习用于考虑初始数据集选择算法中样品的多样性。此外,我们提出了一种新型的主动学习查询策略,该策略使用基于多样性的基于一致性的嵌入方式采样。通过考虑基于一致性的嵌入方案中多样性的一致性信息,该方法可以在半监督的学习环境中选择更多信息的样本来标记。比较实验表明,通过利用未标记的数据的多样性,与先前的主动学习方法相比,该提出的方法在CIFAR-10和CALTECH-101数据集上取得了令人信服的结果。
translated by 谷歌翻译
Semi-supervised learning lately has shown much promise in improving deep learning models when labeled data is scarce. Common among recent approaches is the use of consistency training on a large amount of unlabeled data to constrain model predictions to be invariant to input noise. In this work, we present a new perspective on how to effectively noise unlabeled examples and argue that the quality of noising, specifically those produced by advanced data augmentation methods, plays a crucial role in semi-supervised learning. By substituting simple noising operations with advanced data augmentation methods such as RandAugment and back-translation, our method brings substantial improvements across six language and three vision tasks under the same consistency training framework. On the IMDb text classification dataset, with only 20 labeled examples, our method achieves an error rate of 4.20, outperforming the state-of-the-art model trained on 25,000 labeled examples. On a standard semi-supervised learning benchmark, CIFAR-10, our method outperforms all previous approaches and achieves an error rate of 5.43 with only 250 examples. Our method also combines well with transfer learning, e.g., when finetuning from BERT, and yields improvements in high-data regime, such as ImageNet, whether when there is only 10% labeled data or when a full labeled set with 1.3M extra unlabeled examples is used. 1
translated by 谷歌翻译
半监督学习(SSL)的最新最新方法将一致性正则化与基于置信的伪标记结合在一起。为了获得高质量的伪标签,通常采用高置信度阈值。但是,已经表明,对于远离训练数据的样本,深网的基于软磁性的置信度得分可能很高,因此,即使是高信心不明的样品,伪标签也可能仍然不可靠。在这项工作中,我们提出了伪标记的新观点:而不是依靠模型信心,而是衡量未标记的样本是否可能是“分布”;即,接近当前的培训数据。为了对未标记的样本进行分类是“分布”还是“分发”,我们采用了分布外检测文献中的能量评分。随着培训的进行进展,更不标记的样品成为分配并有助于培训,标记和伪标记的数据可以更好地近似于真正的分布以改善模型。实验表明,我们的基于能量的伪标记方法,尽管从概念上讲简单,但在不平衡的SSL基准测试方面显着优于基于置信的方法,并在类平衡的数据上实现了竞争性能。例如,当不平衡比率高于50时,它会在CIFAR10-LT上产生4-6%的绝对准确性提高。当与最新的长尾SSL方法结合使用时,可以实现进一步的改进。
translated by 谷歌翻译
我们提出了Parse,这是一种新颖的半监督结构,用于学习强大的脑电图表现以进行情感识别。为了减少大量未标记数据与标记数据有限的潜在分布不匹配,Parse使用成对表示对准。首先,我们的模型执行数据增强,然后标签猜测大量原始和增强的未标记数据。然后将其锐化的标签和标记数据的凸组合锐化。最后,进行表示对准和情感分类。为了严格测试我们的模型,我们将解析与我们实施并适应脑电图学习的几种最先进的半监督方法进行了比较。我们对四个基于公共EEG的情绪识别数据集,种子,种子IV,种子V和Amigos(价和唤醒)进行这些实验。该实验表明,我们提出的框架在种子,种子-IV和Amigos(Valence)中的标记样品有限的情况下,取得了总体最佳效果,同时接近种子V和Amigos中的总体最佳结果(达到第二好) (唤醒)。分析表明,我们的成对表示对齐方式通过减少未标记数据和标记数据之间的分布比对来大大提高性能,尤其是当每类仅1个样本被标记时。
translated by 谷歌翻译
Semi-supervised learning (SSL) provides a powerful framework for leveraging unlabeled data when labels are limited or expensive to obtain. SSL algorithms based on deep neural networks have recently proven successful on standard benchmark tasks. However, we argue that these benchmarks fail to address many issues that SSL algorithms would face in real-world applications. After creating a unified reimplementation of various widely-used SSL techniques, we test them in a suite of experiments designed to address these issues. We find that the performance of simple baselines which do not use unlabeled data is often underreported, SSL methods differ in sensitivity to the amount of labeled and unlabeled data, and performance can degrade substantially when the unlabeled dataset contains out-ofdistribution examples. To help guide SSL research towards real-world applicability, we make our unified reimplemention and evaluation platform publicly available. 2 * Equal contribution 2 https://github.com/brain-research/realistic-ssl-evaluation 32nd Conference on Neural Information Processing Systems (NeurIPS 2018),
translated by 谷歌翻译
深度神经网络在大规模标记的数据集的帮助下,在各种任务上取得了出色的表现。然而,这些数据集既耗时又竭尽全力来获得现实的任务。为了减轻对标记数据的需求,通过迭代分配伪标签将伪标签分配给未标记的样本,自我训练被广泛用于半监督学习中。尽管它很受欢迎,但自我训练还是不可靠的,通常会导致训练不稳定。我们的实验研究进一步表明,半监督学习的偏见既来自问题本身,也来自不适当的训练,并具有可能不正确的伪标签,这会在迭代自我训练过程中累积错误。为了减少上述偏见,我们提出了自我训练(DST)。首先,伪标签的生成和利用是由两个独立于参数的分类器头解耦,以避免直接误差积累。其次,我们估计自我训练偏差的最坏情况,其中伪标记函数在标记的样品上是准确的,但在未标记的样本上却尽可能多地犯错。然后,我们通过避免最坏的情况来优化表示形式,以提高伪标签的质量。广泛的实验证明,DST在标准的半监督学习基准数据集上的最先进方法中,平均提高了6.3%,而在13个不同任务上,FIXMATCH的平均水平为18.9%。此外,DST可以无缝地适应其他自我训练方法,并有助于稳定他们在从头开始的培训和预先训练模型的训练的情况下,在培训的情况下进行培训和平衡表现。
translated by 谷歌翻译
We propose a novel end-to-end curriculum learning approach for sparsely labelled animal datasets leveraging large volumes of unlabelled data to improve supervised species detectors. We exemplify the method in detail on the task of finding great apes in camera trap footage taken in challenging real-world jungle environments. In contrast to previous semi-supervised methods, our approach adjusts learning parameters dynamically over time and gradually improves detection quality by steering training towards virtuous self-reinforcement. To achieve this, we propose integrating pseudo-labelling with curriculum learning policies and show how learning collapse can be avoided. We discuss theoretical arguments, ablations, and significant performance improvements against various state-of-the-art systems when evaluating on the Extended PanAfrican Dataset holding approx. 1.8M frames. We also demonstrate our method can outperform supervised baselines with significant margins on sparse label versions of other animal datasets such as Bees and Snapshot Serengeti. We note that performance advantages are strongest for smaller labelled ratios common in ecological applications. Finally, we show that our approach achieves competitive benchmarks for generic object detection in MS-COCO and PASCAL-VOC indicating wider applicability of the dynamic learning concepts introduced. We publish all relevant source code, network weights, and data access details for full reproducibility. The code is available at https://github.com/youshyee/DCL-Detection.
translated by 谷歌翻译