Disentangled Generation with Information Bottleneck for Few-Shot Learning
Not on the map. Why?
Abstract (arXiv)
Few-shot learning (FSL), which aims to classify unseen classes with few samples, is challenging due to data scarcity. Although various generative methods have been explored for FSL, the entangled generation process of these methods exacerbates the distribution shift in FSL, thus greatly limiting the quality of generated samples. To these challenges, we propose a novel Information Bottleneck (IB) based Disentangled Generation Framework for FSL, termed as DisGenIB, that can simultaneously guarantee the discrimination and diversity of generated samples. Specifically, we formulate a novel framework with information bottleneck that applies for both disentangled representation learning and sample generation. Different from existing IB-based methods that can hardly exploit priors, we demonstrate our DisGenIB can effectively utilize priors to further facilitate disentanglement. We further prove in theory that some previous generative and disentanglement methods are special cases of our DisGenIB, which demonstrates the generality of the proposed DisGenIB. Extensive experiments on challenging FSL benchmarks confirm the effectiveness and superiority of DisGenIB, together with the validity of our theoretical analyses. Our codes will be open-source upon acceptance.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 42 of its 57 references that are in the map. First posted on arXiv 29 Nov 2022.
Builds on
42 of 57 references.
References · 42
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
- 2017Prototypical Networks for Few-shot Learningcited by 3,001
- 2016Matching Networks for One Shot Learningcited by 2,246
- 2016Deep Variational Information Bottleneckcited by 915
- 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 858
- 2018Disentangling by Factorisingcited by 614
- 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
- 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 435
- 2018Meta-learning with differentiable closed-form solverscited by 395
- 2018Meta-Transfer Learning for Few-Shot Learningcited by 306
- 2020CLUB: A Contrastive Log-ratio Upper Bound of Mutual Informationcited by 233
- 2021Learning to Diversify for Single Domain Generalizationcited by 170
30 more
- 2020Few-Shot Classification with Feature Map Reconstruction Networkscited by 116
- 2017Generalized Zero-Shot Learning via Synthesized Examplescited by 114
- 2020Interventional Few-Shot Learningcited by 112
- 2020Adversarial Feature Hallucination Networks for Few-Shot Learningcited by 110
- 2019Prototype Rectification for Few-Shot Learningcited by 96
- 2019Adaptive Cross-Modal Few-Shot Learningcited by 95
- 2020Boosting Few-Shot Learning With Adaptive Margin Losscited by 83
- 2020Embedding Propagation: Smoother Manifold for Few-Shot Classificationcited by 79
- 2021Relational Embedding for Few-Shot Classificationcited by 74
- 2018Multi-level Semantic Feature Augmentation for One-shot Learningcited by 62
- 2019Image Deformation Meta-Networks for One-Shot Learningcited by 56
- 2021Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learningcited by 56
- 2020Prototype Completion with Primitive Knowledge for Few-Shot Learningcited by 50
- 2021Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learningcited by 49
- 2020Multimodal Prototypical Networks for Few-shot Learningcited by 48
- 2020Semi-Supervised StyleGAN for Disentanglement Learningcited by 43
- 2021Learning Dynamic Alignment via Meta-filter for Few-shot Learningcited by 41
- 2022Generating Representative Samples for Few-Shot Classificationcited by 39
- 2021Partner-Assisted Learning for Few-Shot Image Classificationcited by 36
- 2022Distilling Robust and Non-Robust Features in Adversarial Examples by Information Bottleneckcited by 30
- 2020Variational Feature Disentangling for Fine-Grained Few-Shot Classificationcited by 26
- 2020Disentangled Information Bottleneckcited by 24
- 2020Spatial Contrastive Learning for Few-Shot Classificationcited by 17
- 2021SEGA: Semantic Guided Attention on Visual Prototype for Few-Shot Learningcited by 15
- 2021Hybrid Graph Neural Networks for Few-Shot Learningcited by 15
- 2020One-Shot Image Classification by Learning to Restore Prototypescited by 14
- 2021Disentangled Feature Representation for Few-shot Image Classificationcited by 12
- 2021Disentangled Variational Information Bottleneck for Multiview Representation Learningcited by 8
- 2021Dizygotic Conditional Variational AutoEncoder for Multi-Modal and Partial Modality Absent Few-Shot Learningcited by 4
- 2022MetaDT: Meta Decision Tree with Class Hierarchy for Interpretable Few-Shot Learningcited by 2
Built on by
Citing papers per year: 2023: 1.
1 paper.