Overcoming challenges in leveraging GANs for few-shot data augmentation
Not on the map. Why?
Abstract (arXiv)
In this paper, we explore the use of GAN-based few-shot data augmentation as a method to improve few-shot classification performance. We perform an exploration into how a GAN can be fine-tuned for such a task (one of which is in a class-incremental manner), as well as a rigorous empirical investigation into how well these models can perform to improve few-shot classification. We identify issues related to the difficulty of training such generative models under a purely supervised regime with very few examples, as well as issues regarding the evaluation protocols of existing works. We also find that in this regime, classification accuracy is highly sensitive to how the classes of the dataset are randomly split. Therefore, we propose a semi-supervised fine-tuning approach as a more pragmatic way forward to address these problems.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 43 of its 59 references that are in the map. First posted on arXiv 30 Mar 2022.
Builds on
43 of 59 references.
References · 43
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2020Denoising Diffusion Probabilistic Modelscited by 20,851
- 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
- 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
- 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
- 2022Generative Adversarial Networkscited by 5,603
- 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
- 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
- 2016Matching Networks for One Shot Learningcited by 2,246
- 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
31 more
- 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
- 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 925
- 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 858
- 2017A Survey on Multi-Task Learningcited by 838
- 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANscited by 515
- 2018A Survey on Deep Transfer Learningcited by 417
- 2018Assessing Generative Models via Precision and Recallcited by 401
- 2018Understanding disentangling in β-VAEcited by 332
- 2017Data Augmentation Generative Adversarial Networkscited by 278
- 2018cGANs with Projection Discriminatorcited by 253
- 2017GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibriumcited by 208
- 2018Low-Shot Learning from Imaginary Datacited by 181
- 2020Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANscited by 132
- 2021Instance-Conditioned GANcited by 119
- 2020Adversarial Feature Hallucination Networks for Few-Shot Learningcited by 110
- 2016Learning feed-forward one-shot learnerscited by 93
- 2018Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizercited by 87
- 2018The Unusual Effectiveness of Averaging in GAN Trainingcited by 73
- 2020Few-Shot Adaptation of Generative Adversarial Networkscited by 64
- 2018Structured Disentangled Representationscited by 62
- 2019Image Deformation Meta-Networks for One-Shot Learningcited by 56
- 2019FIGR: Few-shot Image Generation with Reptilecited by 54
- 2020F2GAN: Fusing-and-Filling GAN for Few-shot Image Generationcited by 29
- 2020DAWSON: A Domain Adaptive Few Shot Generation Frameworkcited by 27
- 2020MatchingGAN: Matching-based Few-shot Image Generationcited by 26
- 2018Generative adversarial interpolative autoencoding: adversarial training on latent space interpolations encourage convex latent distributionscited by 10
- 2019A Meta-Learning Framework for Generalized Zero-Shot Learningcited by 7
- 2018On the Implicit Assumptions of GANscited by 6
- 2017Semi-supervised Conditional GANscited by 3
- 2020Augmentation-Interpolative AutoEncoders for Unsupervised Few-Shot Image Generationcited by 3
- 2019A cost-effective method for improving and re-purposing large, pre-trained GANs by fine-tuning their class-embeddingscited by 1
Built on by
Citing papers per year: 2024: 1.
1 paper.