NP-Match: Towards a New Probabilistic Model for Semi-Supervised Learning
Not on the map. Why?
Abstract (arXiv)
Semi-supervised learning (SSL) has been widely explored in recent years, and it is an effective way of leveraging unlabeled data to reduce the reliance on labeled data. In this work, we adjust neural processes (NPs) to the semi-supervised image classification task, resulting in a new method named NP-Match. NP-Match is suited to this task for two reasons. Firstly, NP-Match implicitly compares data points when making predictions, and as a result, the prediction of each unlabeled data point is affected by the labeled data points that are similar to it, which improves the quality of pseudo-labels. Secondly, NP-Match is able to estimate uncertainty that can be used as a tool for selecting unlabeled samples with reliable pseudo-labels. Compared with uncertainty-based SSL methods implemented with Monte-Carlo (MC) dropout, NP-Match estimates uncertainty with much less computational overhead, which can save time at both the training and the testing phases. We conducted extensive experiments on five public datasets under three semi-supervised image classification settings, namely, the standard semi-supervised image classification, the imbalanced semi-supervised image classification, and the multi-label semi-supervised image classification, and NP-Match outperforms state-of-the-art (SOTA) approaches or achieves competitive results on them, which shows the effectiveness of NP-Match and its potential for SSL. The codes are at https://github.com/Jianf-Wang/NP-Match
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 78 of its 95 references that are in the map. First posted on arXiv 31 Jan 2023.
Builds on
78 of 95 references.
References · 78
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2016Densely Connected Convolutional Networkscited by 6,691
- 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
- 2017On Calibration of Modern Neural Networkscited by 4,860
- 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
- 2014Going Deeper with Convolutionscited by 4,231
- 2016Wide Residual Networkscited by 3,057
- 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
- 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
- 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
38 more
- 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
- 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,057
- 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,054
- 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 987
- 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 806
- 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 704
- 2020Long-tail learning via logit adjustmentcited by 605
- 2021FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labelingcited by 537
- 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 470
- 2016Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learningcited by 441
- 2015Deep Kernel Learningcited by 440
- 2018Conditional Neural Processescited by 421
- 2019Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentationcited by 378
- 2020Meta Pseudo Labelscited by 372
- 2019ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoringcited by 349
- 2019S4L: Self-Supervised Semi-Supervised Learningcited by 335
- 2018Neural Processescited by 307
- 2021In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learningcited by 301
- 2019Attentive Neural Processescited by 280
- 2014Learning with Pseudo-Ensemblescited by 241
- 2021Parametric Contrastive Learningcited by 217
- 2020Rethinking the Value of Labels for Improving Class-Imbalanced Learningcited by 216
- 2021Improving Calibration for Long-Tailed Recognitioncited by 212
- 2021CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learningcited by 174
- 2020Disentangling Label Distribution for Long-tailed Visual Recognitioncited by 172
- 2020CoMatch: Semi-supervised Learning with Contrastive Graph Regularizationcited by 167
- 2018Deep Co-Training for Semi-Supervised Image Recognitioncited by 145
- 2019Convolutional Conditional Neural Processescited by 139
- 2019Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processescited by 131
- 2020Improving model calibration with accuracy versus uncertainty optimizationcited by 123
- 2022SimMatch: Semi-supervised Learning with Similarity Matchingcited by 118
- 2020Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learningcited by 105
- 2021ACE: Ally Complementary Experts for Solving Long-Tailed Recognition in One-Shotcited by 86
- 2021Distributional Robustness Loss for Long-tail Learningcited by 84
- 2021Self Supervision to Distillation for Long-Tailed Visual Recognitioncited by 73
- 2021SimPLE: Similar Pseudo Label Exploitation for Semi-Supervised Classificationcited by 68
- 2021Learning of Visual Relations: The Devil is in the Tailscited by 65
- 2021ABC: Auxiliary Balanced Classifier for Class-imbalanced Semi-supervised Learningcited by 65
50 most cited of 78 All 78 (JSON)
Built on by
Citing papers per year: 2024: 1.
1 paper.