A deep neural network trained on noisy labels is known to quickly lose its power to discriminate clean instances from noisy ones. After the early learning phase has ended, the network memorizes the noisy instances, which leads to a significant degradation in its generalization performance. To resolve this issue, we propose MARVEL (MARgins Via Early Learning), a new robust learning method where the memorization of the noisy instances is curbed. We propose a new test statistic that tracks the goodness of "fit" of every instance based on the epoch-history of its classification margins. If its classification margin is small in a sequence of consecutive learning epochs, that instance is declared noisy and the network abandons learning on it. Consequently, the network first flags a possibly noisy instance, and then waits to see if learning on that instance can be improved and if not, the network learns with confidence that this instance can be safely abandoned. We also propose MARVEL+, where arduous instances can be upweighted, enabling the network to focus and improve its learning on them and consequently its generalization. Experimental results on benchmark datasets with synthetic label noise and real-world datasets show that MARVEL outperforms other baselines consistently across different noise levels, with a significantly larger margin under asymmetric noise.
Deep Learning with noisy labels is a practically challenging problem in weakly supervised learning. The state-of-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 traini…
Deep learning with noisy labels is challenging as deep neural networks have the high capacity to memorize the noisy labels. In this paper, we propose a learning algorithm called Co-matching, which balances the consistency and divergence between two networks by augmentation anchoring. Specifically, we have one network generate anchoring label from its prediction on a weakly-augmented image. Meanwhile, we force its peer network, taking the strongly-augmented version of the same image as input, to generate prediction close to the anchoring label. We then update two networks simultaneously by sele…
Reinforcement learning (RL) has recently proven itself as a powerful instrument for solving complex problems and even surpassed human performance in several challenging applications. This signifies that RL algorithms can be used in the autonomous air combat problem, which has been studied for many years. The complexity of air combat arises from aggressive close-range maneuvers and agile enemy behaviors. In addition to these complexities, there may be uncertainties in real-life scenarios due to sensor errors, which prevent estimation of the actual position of the enemy. In this case, autonomous…
Recent studies on learning with noisy labels have shown remarkable performance by exploiting a small clean dataset. In particular, model agnostic meta-learning-based label correction methods further improve performance by correcting noisy labels on the fly. However, there is no safeguard on the label miscorrection, resulting in unavoidable performance degradation. Moreover, every training step requires at least three back-propagations, significantly slowing down the training speed. To mitigate these issues, we propose a robust and efficient method that learns a label transition matrix on the f…
State Key Laboratory for Novel Software Technology at Nanjing University（南京大学计算机软件新技术国家重点实验室）；Nanjing University（南京大学）
Noisy labels damage the performance of deep networks. For robust learning, a prominent two-stage pipeline alternates between eliminating possible incorrect labels and semi-supervised training. However, discarding part of noisy labels could result in a loss of information, especially when the corruption has a dependency on data, e.g., class-dependent or instance-dependent. Moreover, from the training dynamics of a representative two-stage method DivideMix, we identify the domination of confirmation bias: pseudo-labels fail to correct a considerable amount of noisy labels, and consequently, the …
Supervised deep learning methods require a large repository of annotated data; hence, label noise is inevitable. Training with such noisy data negatively impacts the generalization performance of deep neural networks. To combat label noise, recent state-of-the-art methods employ some sort of sample selection mechanism to select a possibly clean subset of data. Next, an off-the-shelf semi-supervised learning method is used for training where rejected samples are treated as unlabeled data. Our comprehensive analysis shows that current selection methods disproportionately select samples from easy…
Deep neural networks (DNNs) have achieved tremendous success in a variety of applications across many disciplines. Yet, their superior performance comes with the expensive cost of requiring correctly annotated large-scale datasets. Moreover, due to DNNs' rich capacity, errors in training labels can hamper performance. To combat this problem, mean absolute error (MAE) has recently been proposed as a noise-robust alternative to the commonly-used categorical cross entropy (CCE) loss. However, as we show in this paper, MAE can perform poorly with DNNs and challenging datasets. Here, we present a t…
Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）；University of Washington（华盛顿大学）
We introduce a novel method to combat label noise when training deep neural networks for classification. We propose a loss function that permits abstention during training thereby allowing the DNN to abstain on confusing samples while continuing to learn and improve classification performance on the non-abstained samples. We show how such a deep abstaining classifier (DAC) can be used for robust learning in the presence of different types of label noise. In the case of structured or systematic label noise -- where noisy training labels or confusing examples are correlated with underlying featu…
Newcastle University（纽卡斯尔大学）；PUC-Rio（里约热内卢天主教大学）；Universidad Federal Fluminense（弗卢米嫩塞联邦大学）
Tropical diseases like \textit{Chikungunya} and \textit{Zika} have come to prominence in recent years as the cause of serious, long-lasting, population-wide health problems. In large countries like Brasil, traditional disease prevention programs led by health authorities have not been particularly effective. We explore the hypothesis that monitoring and analysis of social media content streams may effectively complement such efforts. Specifically, we aim to identify selected members of the public who are likely to be sensitive to virus combat initiatives that are organised in local communities…
Learning with Open-world Noisy Data via Class-independent Margin in Dual Representation Space
College of Computer Science and Software Engineering, Shenzhen University（深圳大学计算机与软件学院）；Guangdong Provincial Key Laboratory of Intelligent Information Processing（广东省智能信息处理重点实验室）；National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University（深圳大学大数据系统计算技术国家工程实验室）
University of Technology Sydney（悉尼科技大学）；RIKEN（理化学研究所）；Stanford University（斯坦福大学）；University of Tokyo（东京大学）；Paradigm Inc.（第四范式公司）
Deep learning with noisy labels is practically challenging, as the capacity of deep models is so high that they can totally memorize these noisy labels sooner or later during training. Nonetheless, recent studies on the memorization effects of deep neural networks show that they would first memorize training data of clean labels and then those of noisy labels. Therefore in this paper, we propose a new deep learning paradigm called Co-teaching for combating with noisy labels. Namely, we train two deep neural networks simultaneously, and let them teach each other given every mini-batch: firstly,…
National University of Defense Technology（国防科技大学）；University of Surrey（萨里大学）
High quality labeled datasets have allowed deep learning to achieve impressive results on many sound analysis tasks. Yet, it is labor-intensive to accurately annotate large amount of audio data, and the dataset may contain noisy labels in the practical settings. Meanwhile, the deep neural networks are susceptive to those incorrect labeled data because of their outstanding memorization ability. In this paper, we present a novel framework, named CrossFilter, to combat the noisy labels problem for audio tagging. Multiple representations (such as, Logmel and MFCC) are used as the input of our fram…
Linear classifiers and leaky ReLU networks trained by gradient flow on the logistic loss have an implicit bias towards solutions which satisfy the Karush--Kuhn--Tucker (KKT) conditions for margin maximization. In this work we establish a number of settings where the satisfaction of these KKT conditions implies benign overfitting in linear classifiers and in two-layer leaky ReLU networks: the estimators interpolate noisy training data and simultaneously generalize well to test data. The settings include variants of the noisy class-conditional Gaussians considered in previous work as well as new…
Arm Research（Arm研究院）；Arizona State University（亚利桑那州立大学）
The success of deep learning has brought forth a wave of interest in computer hardware design to better meet the high demands of neural network inference. In particular, analog computing hardware has been heavily motivated specifically for accelerating neural networks, based on either electronic, optical or photonic devices, which may well achieve lower power consumption than conventional digital electronics. However, these proposed analog accelerators suffer from the intrinsic noise generated by their physical components, which makes it challenging to achieve high accuracy on deep neural netw…
The Australian National University（澳大利亚国立大学）；Monash University（莫纳什大学）；Data61-CSIRO（澳大利亚联邦科学与工业研究组织Data61）
Neural Architecture Search (NAS) is the game changer in designing robust neural architectures. Architectures designed by NAS outperform or compete with the best manual network designs in terms of accuracy, size, memory footprint and FLOPs. That said, previous studies focus on developing NAS algorithms for clean high quality data, a restrictive and somewhat unrealistic assumption. In this paper, focusing on the differentiable NAS algorithms, we show that vanilla NAS algorithms suffer from a performance loss if class labels are noisy. To combat this issue, we make use of the principle of informa…
Middle East Technical University（中东技术大学）；ASELSAN（阿瑟尔桑公司）
The existence of noisy labels in the dataset causes significant performance degradation for deep neural networks (DNNs). To address this problem, we propose a Meta Soft Label Generation algorithm called MSLG, which can jointly generate soft labels using meta-learning techniques and learn DNN parameters in an end-to-end fashion. Our approach adapts the meta-learning paradigm to estimate optimal label distribution by checking gradient directions on both noisy training data and noise-free meta-data. In order to iteratively update soft labels, meta-gradient descent step is performed on estimated l…
KU Leuven（鲁汶大学）；Samsung AI Center（三星人工智能中心）；Tencent AI lab（腾讯人工智能实验室）；Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
Supervised learning can be viewed as distilling relevant information from input data into feature representations. This process becomes difficult when supervision is noisy as the distilled information might not be relevant. In fact, recent research shows that networks can easily overfit all labels including those that are corrupted, and hence can hardly generalize to clean datasets. In this paper, we focus on the problem of learning with noisy labels and introduce compression inductive bias to network architectures to alleviate this over-fitting problem. More precisely, we revisit one classica…
The University of Melbourne（墨尔本大学）；Shanghai Jiao Tong University（上海交通大学）
Robust loss functions are essential for training accurate deep neural networks (DNNs) in the presence of noisy (incorrect) labels. It has been shown that the commonly used Cross Entropy (CE) loss is not robust to noisy labels. Whilst new loss functions have been designed, they are only partially robust. In this paper, we theoretically show by applying a simple normalization that: any loss can be made robust to noisy labels. However, in practice, simply being robust is not sufficient for a loss function to train accurate DNNs. By investigating several robust loss functions, we find that they su…
Shandong University（山东大学）；Nanjing University（南京大学）；Shandong University of Finance and Economics（山东财经大学）
In non-stationary environments, learning machines usually confront the domain adaptation scenario where the data distribution does change over time. Previous domain adaptation works have achieved great success in theory and practice. However, they always lose robustness in noisy environments where the labels and features of examples from the source domain become corrupted. In this paper, we report our attempt towards achieving accurate noise-robust domain adaptation. We first give a theoretical analysis that reveals how harmful noises influence unsupervised domain adaptation. To eliminate the …
We tackle the problem of learning linear classifiers from noisy datasets in a multiclass setting. The two-class version of this problem was studied a few years ago where the proposed approaches to combat the noise revolve around a Per-ceptron learning scheme fed with peculiar examples computed through a weighted average of points from the noisy training set. We propose to build upon these approaches and we introduce a new algorithm called UMA (for Unconfused Multiclass additive Algorithm) which may be seen as a generalization to the multiclass setting of the previous approaches. In order to ch…
The Chinese University of Hong Kong（香港中文大学）；Tencent（腾讯）
Noisy labels are ubiquitous in real-world datasets, which poses a challenge for robustly training deep neural networks (DNNs) since DNNs can easily overfit to the noisy labels. Most recent efforts have been devoted to defending noisy labels by discarding noisy samples from the training set or assigning weights to training samples, where the weight associated with a noisy sample is expected to be small. Thereby, these previous efforts result in a waste of samples, especially those assigned with small weights. The input $x$ is always useful regardless of whether its observed label $y$ is clean. …
Boston Children’s Hospital（波士顿儿童医院）；Harvard Medical School（哈佛医学院）
Supervised training of deep learning models requires large labeled datasets. There is a growing interest in obtaining such datasets for medical image analysis applications. However, the impact of label noise has not received sufficient attention. Recent studies have shown that label noise can significantly impact the performance of deep learning models in many machine learning and computer vision applications. This is especially concerning for medical applications, where datasets are typically small, labeling requires domain expertise and suffers from high inter- and intra-observer variability…
Deep neural networks (DNNs) exhibit great success on many tasks with the help of large-scale well annotated datasets. However, labeling large-scale data can be very costly and error-prone so that it is difficult to guarantee the annotation quality (i.e., having noisy labels). Training on these noisy labeled datasets may adversely deteriorate their generalization performance. Existing methods either rely on complex training stage division or bring too much computation for marginal performance improvement. In this paper, we propose a Temporal Calibrated Regularization (TCR), in which we utilize …
National Key Laboratory for Novel Software Technology（新型软件技术国家重点实验室）；Nanjing University（南京大学）
Deep learning has achieved excellent performance in various computer vision tasks, but requires a lot of training examples with clean labels. It is easy to collect a dataset with noisy labels, but such noise makes networks overfit seriously and accuracies drop dramatically. To address this problem, we propose an end-to-end framework called PENCIL, which can update both network parameters and label estimations as label distributions. PENCIL is independent of the backbone network structure and does not need an auxiliary clean dataset or prior information about noise, thus it is more general and …
Group Benefits Instances Selection for Data Purification
Nanjing University of Science and Technology（南京理工大学）；Hohai University（河海大学）；Beijing Institute of Technology（北京理工大学）；Beijing Research Institute of Mechanical and Electrical Technology（北京机电工程研究所）；China Ordnance Industrial Standardization Research Institute（中国兵器工业标准化研究所）
The University of Hong Kong（香港大学）；University of California, Los Angeles（加州大学洛杉矶分校）；University of California San Diego（加州大学圣迭戈分校）
Modern machine learning systems such as deep neural networks are often highly over-parameterized so that they can fit the noisy training data exactly, yet they can still achieve small test errors in practice. In this paper, we study this "benign overfitting" phenomenon of the maximum margin classifier for linear classification problems. Specifically, we consider data generated from sub-Gaussian mixtures, and provide a tight risk bound for the maximum margin linear classifier in the over-parameterized setting. Our results precisely characterize the condition under which benign overfitting can o…
We present a unified network for voice separation of an unknown number of speakers. The proposed approach is composed of several separation heads optimized together with a speaker classification branch. The separation is carried out in the time domain, together with parameter sharing between all separation heads. The classification branch estimates the number of speakers while each head is specialized in separating a different number of speakers. We evaluate the proposed model under both clean and noisy reverberant set-tings. Results suggest that the proposed approach is superior to the baseli…
Supervised learning datasets often have privileged information, in the form of features which are available at training time but are not available at test time e.g. the ID of the annotator that provided the label. We argue that privileged information is useful for explaining away label noise, thereby reducing the harmful impact of noisy labels. We develop a simple and efficient method for supervised learning with neural networks: it transfers via weight sharing the knowledge learned with privileged information and approximately marginalizes over privileged information at test time. Our method,…
Universidad de Granada（格拉纳达大学）；Universidad de Sevilla（塞维利亚大学）
In this paper we propose a novel methodology to construct Optimal Classification Trees that takes into account that noisy labels may occur in the training sample. Our approach rests on two main elements: (1) the splitting rules for the classification trees are designed to maximize the separation margin between classes applying the paradigm of SVM; and (2) some of the labels of the training sample are allowed to be changed during the construction of the tree trying to detect the label noise. Both features are considered and integrated together to design the resulting Optimal Classification Tree…
Learning video concept detectors automatically from the big but noisy web data with no additional manual annotations is a novel but challenging area in the multimedia and the machine learning community. A considerable amount of videos on the web are associated with rich but noisy contextual information, such as the title, which provides weak annotations or labels about the video content. To leverage the big noisy web labels, this paper proposes a novel method called WEbly-Labeled Learning (WELL), which is established on the state-of-the-art machine learning algorithm inspired by the learning p…
Tackling Noisy Labels with Network Parameter Additive Decomposition
National University of Defense Technology（国防科技大学）；University of Sydney（悉尼大学）；Beihang University（北京航空航天大学）；University of Science and Technology of China（中国科学技术大学）；Hong Kong Baptist University（香港浸会大学）
ETH Zurich（苏黎世联邦理工学院）；ETH AI Center（苏黎世联邦理工学院人工智能中心）；Max-Planck-Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）
Good generalization performance on high-dimensional data crucially hinges on a simple structure of the ground truth and a corresponding strong inductive bias of the estimator. Even though this intuition is valid for regularized models, in this paper we caution against a strong inductive bias for interpolation in the presence of noise: While a stronger inductive bias encourages a simpler structure that is more aligned with the ground truth, it also increases the detrimental effect of noise. Specifically, for both linear regression and classification with a sparse ground truth, we prove that min…
Pushing One Pair of Labels Apart Each Time in Multi-Label Learning: From Single Positive to Full Labels
College of Computer Science and Technology（计算机科学与技术学院）；College of Artificial Intelligence（人工智能学院）；Nanjing University of Aeronautics and Astronautics（南京航空航天大学）
Nordita, KTH Royal Institute of Technology（北欧理论物理研究所，瑞典皇家理工学院）；Stockholm University（斯德哥尔摩大学）；University of Pittsburgh（匹兹堡大学）；ICSI（国际计算机科学研究所）；UC Berkeley（加州大学伯克利分校）
We provide a general framework for studying recurrent neural networks (RNNs) trained by injecting noise into hidden states. Specifically, we consider RNNs that can be viewed as discretizations of stochastic differential equations driven by input data. This framework allows us to study the implicit regularization effect of general noise injection schemes by deriving an approximate explicit regularizer in the small noise regime. We find that, under reasonable assumptions, this implicit regularization promotes flatter minima; it biases towards models with more stable dynamics; and, in classificat…
