# Generating Representative Samples for Few-Shot Classification

arXiv: https://arxiv.org/abs/2205.02918 · HTML: https://mlsanity.com/paper/2205.02918/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- Builds on 69 of its 93 references that are in the map.
- First posted on arXiv 5 May 2022.

## Builds on (most cited first, 30 of 69)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [A Closer Look at Few-shot Classification](https://mlsanity.com/paper/1904.04232/) (2019)
- [Unsupervised Image-to-Image Translation Networks](https://mlsanity.com/paper/1703.00848/) (2017)
- [Meta-Learning with Implicit Gradients](https://mlsanity.com/paper/1909.04630/) (2019)
- [Generalizing from a Few Examples: A Survey on Few-Shot Learning](https://mlsanity.com/paper/1904.05046/) (2019)
- [Meta-Learning with Differentiable Convex Optimization](https://mlsanity.com/paper/1904.03758/) (2019)
- [Meta-Learning for Semi-Supervised Few-Shot Classification](https://mlsanity.com/paper/1803.00676/) (2018)
- [Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?](https://mlsanity.com/paper/2003.11539/) (2020)
- [TADAM: Task dependent adaptive metric for improved few-shot learning](https://mlsanity.com/paper/1805.10123/) (2018)
- [Meta-SGD: Learning to Learn Quickly for Few-Shot Learning](https://mlsanity.com/paper/1707.09835/) (2017)
- [Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions](https://mlsanity.com/paper/1812.03664/) (2018)
- [Data Augmentation Generative Adversarial Networks](https://mlsanity.com/paper/1711.04340/) (2017)
- [Cross Attention Network for Few-shot Classification](https://mlsanity.com/paper/1910.07677/) (2019)
- [Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders](https://mlsanity.com/paper/1812.01784/) (2018)
- [SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning](https://mlsanity.com/paper/1911.04623/) (2019)
- [Low-Shot Learning from Imaginary Data](https://mlsanity.com/paper/1801.05401/) (2018)
- [Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning](https://mlsanity.com/paper/2003.04390/) (2020)
- [Free Lunch for Few-shot Learning: Distribution Calibration](https://mlsanity.com/paper/2101.06395/) (2021)
- [Learning a Deep Embedding Model for Zero-Shot Learning](https://mlsanity.com/paper/1611.05088/) (2016)
- [Charting the Right Manifold: Manifold Mixup for Few-shot Learning](https://mlsanity.com/paper/1907.12087/) (2019)
- [Negative Margin Matters: Understanding Margin in Few-shot Classification](https://mlsanity.com/paper/2003.12060/) (2020)
- [Self-Supervision with Superpixels: Training Few-shot Medical Image Segmentation without Annotation](https://mlsanity.com/paper/2007.09886/) (2020)

## Built on by (most cited first, 30 of 39)

- [A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2205.06743/) (2022)
- [Generating images of rare concepts using pre-trained diffusion models](https://mlsanity.com/paper/2304.14530/) (2023)
- [Zero-shot Object Counting](https://mlsanity.com/paper/2303.02001/) (2023)
- [Norm-guided latent space exploration for text-to-image generation](https://mlsanity.com/paper/2306.08687/) (2023)
- [Generating Features with Increased Crop-related Diversity for Few-Shot Object Detection](https://mlsanity.com/paper/2304.05096/) (2023)
- [Simple Semantic-Aided Few-Shot Learning](https://mlsanity.com/paper/2311.18649/) (2023)
- [Reference Twice: A Simple and Unified Baseline for Few-Shot Instance Segmentation](https://mlsanity.com/paper/2301.01156/) (2023)
- [Zero-Shot Object Counting with Language-Vision Models](https://mlsanity.com/paper/2309.13097/) (2023)
- [Assessing Sample Quality via the Latent Space of Generative Models](https://mlsanity.com/paper/2407.15171/) (2024)
- [Making Large Vision Language Models to be Good Few-shot Learners](https://mlsanity.com/paper/2408.11297/) (2024)
- [VT-FSL: Bridging Vision and Text with LLMs for Few-Shot Learning](https://mlsanity.com/paper/2509.25033/) (2025)
- [Advancing Incremental Few-shot Semantic Segmentation via Semantic-guided Relation Alignment and Adaptation](https://mlsanity.com/paper/2305.10868/) (2023)
- [Shadow Removal Refinement via Material-Consistent Shadow Edges](https://mlsanity.com/paper/2409.06848/) (2024)
- [Few-shot Personalized Scanpath Prediction](https://mlsanity.com/paper/2504.05499/) (2025)
- [Spatio-temporal Decoupled Knowledge Compensator for Few-Shot Action Recognition](https://mlsanity.com/paper/2602.18043/) (2026)
- [Disentangled Representation Learning with Transmitted Information Bottleneck](https://mlsanity.com/paper/2311.01686/) (2023)
- [Controlling the Fidelity and Diversity of Deep Generative Models via Pseudo Density](https://mlsanity.com/paper/2407.08659/) (2024)
- [VaMP: Variational Multi-Modal Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2511.22664/) (2025)
- [A Statistical Model for Predicting Generalization in Few-Shot Classification](https://mlsanity.com/paper/2212.06461/) (2022)
- [Robust Meta-Representation Learning via Global Label Inference and Classification](https://mlsanity.com/paper/2212.11702/) (2022)
- [Weighting Pseudo-Labels via High-Activation Feature Index Similarity and Object Detection for Semi-Supervised Segmentation](https://mlsanity.com/paper/2407.12630/) (2024)
- [DVLA-RL: Dual-Level Vision-Language Alignment with Reinforcement Learning Gating for Few-Shot Learning](https://mlsanity.com/paper/2602.00795/) (2026)
- [Disentangled Generation with Information Bottleneck for Few-Shot Learning](https://mlsanity.com/paper/2211.16185/) (2022)
- [Trustworthy Representation Learning Across Domains](https://mlsanity.com/paper/2308.12315/) (2023)
- [Task Attribute Distance for Few-Shot Learning: Theoretical Analysis and Applications](https://mlsanity.com/paper/2403.03535/) (2024)
- [Tiny models from tiny data: Textual and null-text inversion for few-shot distillation](https://mlsanity.com/paper/2406.03146/) (2024)
- [Knowledge Adaptation Network for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2409.11770/) (2024)
- [CORA: Consistency-Guided Semi-Supervised Framework for Reasoning Segmentation](https://mlsanity.com/paper/2511.17755/) (2025)
- [GFPL: Generative Federated Prototype Learning for Resource-Constrained and Data-Imbalanced Vision Task](https://mlsanity.com/paper/2602.21873/) (2026)
- [Knowledge Transfer-Driven Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2306.10942/) (2023)

## Abstract (arXiv)

Few-shot learning (FSL) aims to learn new categories with a few visual samples per class. Few-shot class representations are often biased due to data scarcity. To mitigate this issue, we propose to generate visual samples based on semantic embeddings using a conditional variational autoencoder (CVAE) model. We train this CVAE model on base classes and use it to generate features for novel classes. More importantly, we guide this VAE to strictly generate representative samples by removing non-representative samples from the base training set when training the CVAE model. We show that this training scheme enhances the representativeness of the generated samples and therefore, improves the few-shot classification results. Experimental results show that our method improves three FSL baseline methods by substantial margins, achieving state-of-the-art few-shot classification performance on miniImageNet and tieredImageNet datasets for both 1-shot and 5-shot settings. Code is available at: https://github.com/cvlab-stonybrook/fsl-rsvae.