Pseudo-labels are confident predictions made on unlabeled target data by a classifier trained on labeled source data. They are widely used for adapting a model to unlabeled data, e.g., in a semi-supervised learning setting.
Our key insight is that pseudo-labels are naturally imbalanced due to intrinsic data similarity, even when a model is trained on balanced source data and evaluated on balanced target data. If we address this previously unknown imbalanced classification problem arising from pseudo-labels instead of ground-truth training labels, we could remove model biases towards false majorities created by pseudo-labels.
We propose a novel and effective debiased learning method with pseudo-labels, based on counterfactual reasoning and adaptive margins: The former removes the classifier response bias, whereas the latter adjusts the margin of each class according to the imbalance of pseudo-labels. Validated by extensive experimentation, our simple debiased learning delivers significant accuracy gains over the state-of-the-art on ImageNet-1K: 26% for semi-supervised learning with 0.2% annotations and 9% for zero-shot learning. Our code is available at: https://github.com/frank-xwang/debiased-pseudo-labeling.
Seoul National University（首尔国立大学）；Adobe Research（奥多比研究院）
Dataset bias is a critical challenge in machine learning since it often leads to a negative impact on a model due to the unintended decision rules captured by spurious correlations. Although existing works often handle this issue based on human supervision, the availability of the proper annotations is impractical and even unrealistic. To better tackle the limitation, we propose a simple but effective unsupervised debiasing technique. Specifically, we first identify pseudo-attributes based on the results from clustering performed in the feature embedding space even without an explicit bias att…
Deep neural networks achieve remarkable performances on a wide range of tasks with the aid of large-scale labeled datasets. Yet these datasets are time-consuming and labor-exhaustive to obtain on realistic tasks. To mitigate the requirement for labeled data, self-training is widely used in semi-supervised learning by iteratively assigning pseudo labels to unlabeled samples. Despite its popularity, self-training is well-believed to be unreliable and often leads to training instability. Our experimental studies further reveal that the bias in semi-supervised learning arises from both the problem…
National Institute of Information and Communications Technology（信息通信研究机构）
Herein, we generate pseudo-features based on the multivariate probability distributions obtained from the feature maps in layers of trained deep neural networks. Further, we augment the minor-class data based on these generated pseudo-features to overcome the imbalanced data problems. The proposed method, i.e., cavity filling, improves the deep learning capabilities in several problems because all the real-world data are observed to be imbalanced.
Recent state-of-the-art methods in imbalanced semi-supervised learning (SSL) rely on confidence-based pseudo-labeling with consistency regularization. To obtain high-quality pseudo-labels, a high confidence threshold is typically adopted. However, it has been shown that softmax-based confidence scores in deep networks can be arbitrarily high for samples far from the training data, and thus, the pseudo-labels for even high-confidence unlabeled samples may still be unreliable. In this work, we present a new perspective of pseudo-labeling for imbalanced SSL. Without relying on model confidence, w…
The capability of the traditional semi-supervised learning (SSL) methods is far from real-world application due to severely biased pseudo-labels caused by (1) class imbalance and (2) class distribution mismatch between labeled and unlabeled data. This paper addresses such a relatively under-explored problem. First, we propose a general pseudo-labeling framework that class-adaptively blends the semantic pseudo-label from a similarity-based classifier to the linear one from the linear classifier, after making the observation that both types of pseudo-labels have complementary properties in terms…
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；NLPR, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所模式识别国家重点实验室）
Partial-label learning (PLL) is an important branch of weakly supervised learning where the single ground truth resides in a set of candidate labels, while the research rarely considers the label imbalance. A recent study for imbalanced partial-Label learning proposed that the combinatorial challenge of partial-label learning and long-tail learning lies in matching between a decent marginal prior distribution with drawing the pseudo labels. However, we believe that even if the pseudo label matches the prior distribution, the tail classes will still be difficult to learn because the total weigh…
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）；Samsung Advanced Institute of Technology（三星综合技术院）；AItrics
While semi-supervised learning (SSL) has proven to be a promising way for leveraging unlabeled data when labeled data is scarce, the existing SSL algorithms typically assume that training class distributions are balanced. However, these SSL algorithms trained under imbalanced class distributions can severely suffer when generalizing to a balanced testing criterion, since they utilize biased pseudo-labels of unlabeled data toward majority classes. To alleviate this issue, we formulate a convex optimization problem to softly refine the pseudo-labels generated from the biased model, and develop a…
Xi’an Jiaotong University（西安交通大学）；Xidian University（西安电子科技大学）；City University of Hong Kong（香港城市大学）；Macau University of Science and Technology（澳门科技大学）；Peng Cheng Laboratory（鹏城实验室）
Pseudo-labeling has proven to be a promising semi-supervised learning (SSL) paradigm. Existing pseudo-labeling methods commonly assume that the class distributions of training data are balanced. However, such an assumption is far from realistic scenarios and thus severely limits the performance of current pseudo-labeling methods under the context of class-imbalance. To alleviate this problem, we design a bias adaptive classifier that targets the imbalanced SSL setups. The core idea is to automatically assimilate the training bias caused by class imbalance via the bias adaptive classifier, whic…
Imbalanced Semi-Supervised Learning via Label Refinement and Threshold Adjustment
College of Biomedical Engineering, Fudan University, Shanghai, China（复旦大学生物医学工程学院，上海，中国）；FMRIB Centre, Oxford Centre for Integrative Neuroimaging (OxCIN), University of Oxford, Oxford, UK（牛津大学FMRIB研究中心，牛津大学整合神经影像中心（OxCIN），牛津，英国）；School of Computer Science, University of Sheffield, Sheffield, UK（谢菲尔德大学计算机科学学院，谢菲尔德，英国）；Department of Engineering Science, University of Oxford, Oxford, UK（牛津大学工程科学系，牛津，英国）
Learning from positive and unlabeled (PU) data is a setting where the learner only has access to positive and unlabeled samples while having no information on negative examples. Such PU setting is of great importance in various tasks such as medical diagnosis, social network analysis, financial markets analysis, and knowledge base completion, which also tend to be intrinsically imbalanced, i.e., where most examples are actually negatives. Most existing approaches for PU learning, however, only consider artificially balanced datasets and it is unclear how well they perform in the realistic scen…
Uncertainty-aware Pseudo-label Selection for Positive-Unlabeled Learning
Ludwig-Maximilians-Universität München（慕尼黑大学）；Helmholtz Zentrum München—German Research Center for Environmental Health（亥姆霍兹慕尼黑中心——德国环境健康研究中心）；Munich Center for Machine Learning（慕尼黑机器学习中心）；Fraunhofer Institute for Integrated Circuits IIS（弗劳恩霍夫集成电路研究所）；Technical University of Munich（慕尼黑工业大学）
Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；Nanjing University（南京大学）
Traditional supervised learning requires ground truth labels for the training data, whose collection can be difficult in many cases. Recently, crowdsourcing has established itself as an efficient labeling solution through resorting to non-expert crowds. To reduce the labeling error effects, one common practice is to distribute each instance to multiple workers, whereas each worker only annotates a subset of data, resulting in the {\it sparse annotation} phenomenon. In this paper, we note that when meeting with class-imbalance, i.e., when the ground truth labels are {\it class-imbalanced}, the …
Nanjing University（南京大学）；Tencent AI Lab（腾讯人工智能实验室）
Learning with Noisy Labels (LNL) has attracted significant attention from the research community. Many recent LNL methods rely on the assumption that clean samples tend to have "small loss". However, this assumption always fails to generalize to some real-world cases with imbalanced subpopulations, i.e., training subpopulations varying in sample size or recognition difficulty. Therefore, recent LNL methods face the risk of misclassifying those "informative" samples (e.g., hard samples or samples in the tail subpopulations) into noisy samples, leading to poor generalization performance. To addr…
ImGCL: Revisiting Graph Contrastive Learning on Imbalanced Node Classification
Institute for Interdisciplinary Information Sciences (IIIS), Tsinghua University（清华大学交叉信息研究院）；Tencent AI Lab（腾讯人工智能实验室）；Hong Kong University of Science and Technology（香港科技大学）
Understanding and Mitigating the Bias in Sample Selection for Learning with Noisy Labels
College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）；Singapore University of Technology and Design（新加坡科技设计大学）；School of Software, Zhejiang University（浙江大学软件学院）
Long-Tailed Semi-Supervised Learning (LTSSL) aims to learn from class-imbalanced data where only a few samples are annotated. Existing solutions typically require substantial cost to solve complex optimization problems, or class-balanced undersampling which can result in information loss. In this paper, we present the TRAS (TRAnsfer and Share) to effectively utilize long-tailed semi-supervised data. TRAS transforms the imbalanced pseudo-label distribution of a traditional SSL model via a delicate function to enhance the supervisory signals for minority classes. It then transfers the distributi…
Recent state-of-the-art methods in semi-supervised learning (SSL) combine consistency regularization with confidence-based pseudo-labeling. To obtain high-quality pseudo-labels, a high confidence threshold is typically adopted. However, it has been shown that softmax-based confidence scores in deep networks can be arbitrarily high for samples far from the training data, and thus, the pseudo-labels for even high-confidence unlabeled samples may still be unreliable. In this work, we present a new perspective of pseudo-labeling: instead of relying on model confidence, we instead measure whether a…
Resilient Class-Incremental Learning: on the Interplay of Drifting, Unlabelled and Imbalanced Data Streams
KIOS Research and Innovation Center of Excellence, University of Cyprus（希腊塞浦路斯大学KIOS研究中心）；Department of Electrical and Computer Engineering, University of Cyprus（塞浦路斯大学电气与计算机工程系）
Multimodal Deep Generative Model for Semi-Supervised Learning under Class Imbalance
Department of Industrial and Systems Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea（工业与系统工程系，韩国科学技术院（KAIST），大田，大韩民国）
When there are unlabeled Out-Of-Distribution (OOD) data from other classes, Semi-Supervised Learning (SSL) methods suffer from severe performance degradation and even get worse than merely training on labeled data. In this paper, we empirically analyze Pseudo-Labeling (PL) in class-mismatched SSL. PL is a simple and representative SSL method that transforms SSL problems into supervised learning by creating pseudo-labels for unlabeled data according to the model's prediction. We aim to answer two main questions: (1) How do OOD data influence PL? (2) What is the proper usage of OOD data with PL?…
Carnegie Mellon University（卡内基梅隆大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Microsoft Research Asia（微软亚洲研究院）；Mohamed bin Zayed University of AI（穆罕默德·本·扎耶德人工智能大学）
The critical challenge of Semi-Supervised Learning (SSL) is how to effectively leverage the limited labeled data and massive unlabeled data to improve the model's generalization performance. In this paper, we first revisit the popular pseudo-labeling methods via a unified sample weighting formulation and demonstrate the inherent quantity-quality trade-off problem of pseudo-labeling with thresholding, which may prohibit learning. To this end, we propose SoftMatch to overcome the trade-off by maintaining both high quantity and high quality of pseudo-labels during training, effectively exploiting…
MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；Rutgers University（罗格斯大学）
State-of-the-art (SOTA) semi-supervised learning (SSL) methods have been highly successful in leveraging a mix of labeled and unlabeled data by combining techniques of consistency regularization and pseudo-labeling. During pseudo-labeling, the model's predictions on unlabeled data are used for training and thus, model calibration is important in mitigating confirmation bias. Yet, many SOTA methods are optimized for model performance, with little focus directed to improve model calibration. In this work, we empirically demonstrate that model calibration is strongly correlated with model perform…
Center for Research in Computer Vision, UCF（中佛罗里达大学计算机视觉研究中心）
Deep learning is pushing the state-of-the-art in many computer vision applications. However, it relies on large annotated data repositories, and capturing the unconstrained nature of the real-world data is yet to be solved. Semi-supervised learning (SSL) complements the annotated training data with a large corpus of unlabeled data to reduce annotation cost. The standard SSL approach assumes unlabeled data are from the same distribution as annotated data. Recently, a more realistic SSL problem, called open-world SSL, is introduced, where the unannotated data might contain samples from unknown c…
MultiMatch: Multihead Consistency Regularization Matching for Semi-Supervised Text Classification
National University of Science and Technology POLITEHNICA Bucharest（波兰技术大学科学与技术国立大学）；University of Illinois Chicago（伊利诺伊大学芝加哥分校）；NVIDIA（NVIDIA公司）；Renius Technologies（Renius技术公司）
Beijing Institute of Technology（北京理工大学）；Tsinghua University（清华大学）；Inceptio Technology（嬴彻科技）
Self-training has greatly facilitated domain adaptive semantic segmentation, which iteratively generates pseudo labels on unlabeled target data and retrains the network. However, realistic segmentation datasets are highly imbalanced, pseudo labels are typically biased to the majority classes and basically noisy, leading to an error-prone and suboptimal model. In this paper, we propose a simple region-based active learning approach for semantic segmentation under a domain shift, aiming to automatically query a small partition of image regions to be labeled while maximizing segmentation performa…
Exploring a Hybrid Deep Learning Approach for Anomaly Detection in Mental Healthcare Provider Billing: Addressing Label Scarcity through Semi-Supervised Anomaly Detection
Informatics Institute, University of Amsterdam（阿姆斯特丹大学信息学院）；Department of Computer Science and Technology, SUNY Empire State University（SUNY埃默里州立大学计算机科学与技术系）
AllMatch: Exploiting All Unlabeled Data for Semi-Supervised Learning
National Key Laboratory of General Artificial Intelligence（通用人工智能国家重点实验室）；School of Intelligence Science and Technology, Peking University（北京大学智能科学与技术学院）
Extracting Clean and Balanced Subset for Noisy Long-tailed Classification
Shenzhen Research Institute of Big Data（深圳大数据研究院）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；CSIRO’s Data61（联邦科学与工业研究组织数据61部门）；The University of Sydney（悉尼大学）；School of Artificial Intelligence, Jilin University（吉林大学人工智能学院）
Machine learning fairness concerns about the biases towards certain protected or sensitive group of people when addressing the target tasks. This paper studies the debiasing problem in the context of image classification tasks. Our data analysis on facial attribute recognition demonstrates (1) the attribution of model bias from imbalanced training data distribution and (2) the potential of adversarial examples in balancing data distribution. We are thus motivated to employ adversarial example to augment the training data for visual debiasing. Specifically, to ensure the adversarial generalizat…
Self-Discriminative Modeling for Anomalous Graph Detection
Institute of Data Science（数据科学研究所）；National University of Singapore（新加坡国立大学）；Shenzhen Research Institute of Big Data（深圳大数据研究院）；School of Data Science（数据科学学院）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
