On the link between generative semi-supervised learning and generative open-set recognition
Not on the map. Why?
Abstract (arXiv)
This study investigates the relationship between semi-supervised learning (SSL, which is training off partially labelled datasets) and open-set recognition (OSR, which is classification with simultaneous novelty detection) under the context of generative adversarial networks (GANs). Although no previous study has formally linked SSL and OSR, their respective methods share striking similarities. Specifically, SSL-GANs and OSR-GANs require their generators to produce 'bad-looking' samples which are used to regularise their classifier networks. We hypothesise that the definitions of bad-looking samples in SSL and OSR represents the same concept and realises the same goal. More formally, bad-looking samples lie in the complementary space, which is the area between and around the boundaries of the labelled categories within the classifier's embedding space. By regularising a classifier with samples in the complementary space, classifiers achieve improved generalisation for SSL and also generalise the open space for OSR. To test this hypothesis, we compare a foundational SSL-GAN with the state-of-the-art OSR-GAN under the same SSL-OSR experimental conditions. Our results find that SSL-GANs achieve near identical results to OSR-GANs, proving the SSL-OSR link. Subsequently, to further this new research path, we compare several SSL-GANs various SSL-OSR setups which this first benchmark results. A combined framework of SSL-OSR certainly improves the practicality and cost-efficiency of classifier training, and so further theoretical and application studies are also discussed.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 21 of its 58 references that are in the map. First posted on arXiv 21 Mar 2023.
Builds on
21 of 58 references.
References · 21
- 2022Generative Adversarial Networkscited by 5,603
- 2016Improved Techniques for Training GANscited by 2,938
- 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 470
- 2020Meta Pseudo Labelscited by 372
- 2018Regularisation of Neural Networks by Enforcing Lipschitz Continuitycited by 311
- 2018Recent Advances in Open Set Recognition: A Surveycited by 309
- 2018Adversarially Learned One-Class Classifier for Novelty Detectioncited by 202
- 2019OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representationscited by 199
- 2021Adversarial Reciprocal Points Learning for Open Set Recognitioncited by 153
- 2016Semi-Supervised Learning with Generative Adversarial Networkscited by 103
- 2021Can multi-label classification networks know what they don't know?cited by 100
- 2017Good Semi-supervised Learning that Requires a Bad GANcited by 85
9 more
- 2020Multi-Task Curriculum Framework for Open-Set Semi-Supervised Learningcited by 82
- 2016Detecting Unexpected Obstacles for Self-Driving Cars: Fusing Deep Learning and Geometric Modelingcited by 28
- 2021Automatic Cough Classification for Tuberculosis Screening in a Real-World Environmentcited by 17
- 2019Triple Generative Adversarial Networkscited by 11
- 2019HexaGAN: Generative Adversarial Nets for Real World Classificationcited by 10
- 2018Novelty Detection with GANcited by 8
- 2022AuxMix: Semi-Supervised Learning with Unconstrained Unlabeled Datacited by 4
- 2019Semi-Supervised Self-Growing Generative Adversarial Networks for Image Recognitioncited by 3
- 2019Semi-supervised Learning using Adversarial Training with Good and Bad Samplescited by 2
Built on by
Citing papers per year: 2023: 1.
1 paper.