# Low-shot Learning via Covariance-Preserving Adversarial Augmentation Networks

arXiv: https://arxiv.org/abs/1810.11730 · HTML: https://mlsanity.com/paper/1810.11730/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Oct 2018.

## Built on by (most cited first, 30 of 35)

- [Free Lunch for Few-shot Learning: Distribution Calibration](https://mlsanity.com/paper/2101.06395/) (2021)
- [A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2205.06743/) (2022)
- [Hallucination Improves Few-Shot Object Detection](https://mlsanity.com/paper/2105.01294/) (2021)
- [Matching Feature Sets for Few-Shot Image Classification](https://mlsanity.com/paper/2204.00949/) (2022)
- [SEGA: Semantic Guided Attention on Visual Prototype for Few-Shot Learning](https://mlsanity.com/paper/2111.04316/) (2021)
- [Adaptive Distribution Calibration for Few-Shot Learning with Hierarchical Optimal Transport](https://mlsanity.com/paper/2210.04144/) (2022)
- [What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data](https://mlsanity.com/paper/2106.06410/) (2021)
- [Prototypical Fine-tuning: Towards Robust Performance Under Varying Data Sizes](https://mlsanity.com/paper/2211.13638/) (2022)
- [Dynamic Flows on Curved Space Generated by Labeled Data](https://mlsanity.com/paper/2302.00061/) (2023)
- [Dense Vision Transformer Compression with Few Samples](https://mlsanity.com/paper/2403.18708/) (2024)
- [Fine-Grained Few Shot Learning with Foreground Object Transformation](https://mlsanity.com/paper/2109.05719/) (2021)
- [Instance-Conditioned GAN Data Augmentation for Representation Learning](https://mlsanity.com/paper/2303.09677/) (2023)
- [Approximating Human-Like Few-shot Learning with GPT-based Compression](https://mlsanity.com/paper/2308.06942/) (2023)
- [Few-Shot Non-Parametric Learning with Deep Latent Variable Model](https://mlsanity.com/paper/2206.11573/) (2022)
- [Exploring Category-correlated Feature for Few-shot Image Classification](https://mlsanity.com/paper/2112.07224/) (2021)
- [Metric Based Few-Shot Graph Classification](https://mlsanity.com/paper/2206.03695/) (2022)
- [Practical Continual Forgetting for Pre-trained Vision Models](https://mlsanity.com/paper/2501.09705/) (2025)
- [Reinforcing Generated Images via Meta-learning for One-Shot Fine-Grained Visual Recognition](https://mlsanity.com/paper/2204.10689/) (2022)
- [Exploring Effective Knowledge Transfer for Few-shot Object Detection](https://mlsanity.com/paper/2210.02021/) (2022)
- [Hint-Aug: Drawing Hints from Foundation Vision Transformers Towards Boosted Few-Shot Parameter-Efficient Tuning](https://mlsanity.com/paper/2304.12520/) (2023)
- [Few-shot Learning via Dependency Maximization and Instance Discriminant Analysis](https://mlsanity.com/paper/2109.02820/) (2021)
- [Semantics-driven Attentive Few-shot Learning over Clean and Noisy Samples](https://mlsanity.com/paper/2201.03043/) (2022)
- [Population Template-Based Brain Graph Augmentation for Improving One-Shot Learning Classification](https://mlsanity.com/paper/2212.07790/) (2022)
- [Dual Adversarial Alignment for Realistic Support-Query Shift Few-shot Learning](https://mlsanity.com/paper/2309.02088/) (2023)
- [Detail Reinforcement Diffusion Model: Augmentation Fine-Grained Visual Categorization in Few-Shot Conditions](https://mlsanity.com/paper/2309.08097/) (2023)
- [Trajectory-aware Principal Manifold Framework for Data Augmentation and Image Generation](https://mlsanity.com/paper/2310.07801/) (2023)
- [FSL-Rectifier: Rectify Outliers in Few-Shot Learning via Test-Time Augmentation](https://mlsanity.com/paper/2402.18292/) (2024)
- [FLIER: Few-shot Language Image Models Embedded with Latent Representations](https://mlsanity.com/paper/2410.07648/) (2024)
- [Few-Shot Generalized Category Discovery With Retrieval-Guided Decision Boundary Enhancement](https://mlsanity.com/paper/2506.16728/) (2025)
- [Dual Path Structural Contrastive Embeddings for Learning Novel Objects](https://mlsanity.com/paper/2112.12359/) (2021)

## Abstract (arXiv)

Deep neural networks suffer from over-fitting and catastrophic forgetting when trained with small data. One natural remedy for this problem is data augmentation, which has been recently shown to be effective. However, previous works either assume that intra-class variances can always be generalized to new classes, or employ naive generation methods to hallucinate finite examples without modeling their latent distributions. In this work, we propose Covariance-Preserving Adversarial Augmentation Networks to overcome existing limits of low-shot learning. Specifically, a novel Generative Adversarial Network is designed to model the latent distribution of each novel class given its related base counterparts. Since direct estimation of novel classes can be inductively biased, we explicitly preserve covariance information as the `variability' of base examples during the generation process. Empirical results show that our model can generate realistic yet diverse examples, leading to substantial improvements on the ImageNet benchmark over the state of the art.