A brief introduction to weakly supervised learning

By Zhi-Hua Zhou. 2018

1,874 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

A Survey on Data Collection for Machine Learning: A Big Data - AI Integration Perspective (2018, background): “As a result, weak supervision techniques [151], [152], [153] have become increasingly popular where the idea is to”
Generalizing from a Few Examples (2019, background): “• Weakly supervised learning [163] learns from experience E containing only weak supervision (such as incomplete, inexact, inaccurate or noisy supervised information).”
Image Segmentation Using Deep Learning: A Survey (2020, background): “few shot) learning [186] and unsupervised learning [187] are becoming very active research areas.”
WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research (2023, background): “Theterm“weakly-labeleddataset”isderived fromthedomainofweaksupervisionorweaklysupervised learning[42].”
Deep Learning for Whole Slide Image Analysis: An Overview (2019, methodology): “(16) subsequently used k-means clustering and found the most discriminative clusters of patches by training CNNs in a weakly supervised manner (42).”
Type4Py: Practical Deep Similarity Learning-Based Type Inference for Python (2021, background): “However, this can be considered as a weakly supervision learning problem [66], meaning that inferred types by the static tool might be noisy or imprecise despite the pre-processing steps.”
See Better Before Looking Closer: Weakly Supervised Data Augmentation Network for Fine-Grained Visual Classification (2019, background): “Weakly supervised learning is an umbrella term that covers a variety of studies that attempt to construct predictive models by learning with weak supervision [40].”
Small Sample Learning in Big Data Era (2018, background): “Different from SSL with few annotated samples, weakly-supervised learning usually contains more annotated information, while is coarse-grained or noisy, whose supervised information is inexact, inaccurate or incomplete (Zhou, 2017).”
A Survey on Curriculum Learning (2021, background): “Weakly-supervised setting includes three typical types [147], all of which are enhanced by CL denoising.”
A Survey of Deep Learning Techniques for Weed Detection from Images (2021, background): “Semi-supervised (Chapelle et al., 2009; X.-Y. Zhang et al., 2019) or weakly supervised (Durand et al., 2017; Zhou, 2018) approaches could be employed to address this problem.”
ADBench: Anomaly Detection Benchmark (2022, background): “In ADBench, semi-supervision mostly refers to incomplete label learning in weak-supervision (see [206]).”
Multi-Stage Self-Supervised Learning for Graph Convolutional Networks (2019, background): “However, to the best of our knowledge, there is hardly any work about graphs focusing on weakly supervised setting (Zhou 2017), especially learning a classiﬁcation model with few examples from each class.”
Combating Noisy Labels by Agreement: A Joint Training Method with Co-Regularization (2020, background): “Semi-supervised learning also belongs to the family of weakly supervised learning frameworks [15, 18, 22, 26, 27, 31, 47].”
Self-Supervised Learning in Remote Sensing: A review (2022, background): “In fact, numerous alternatives to vanilla supervised learning have been studied, such as unsupervised learning [3], semi-supervised learning [4], weakly supervised learning [5] and meta-learning [6].”
Multi-Label Learning with Global and Local Label Correlation (2017, background): “Thus, some labelsmay bemissing from the training set, which is a kind of weakly supervised learning [51].”