# Enhancing Few-Shot Image Classification with Unlabelled Examples

arXiv: https://arxiv.org/abs/2006.12245 · HTML: https://mlsanity.com/paper/2006.12245/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jun 2020.

## Built on by (most cited first, 30 of 32)

- [A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2205.06743/) (2022)
- [Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference](https://mlsanity.com/paper/2204.07305/) (2022)
- [Cross-domain Few-shot Learning with Task-specific Adapters](https://mlsanity.com/paper/2107.00358/) (2021)
- [Adversarial Feature Augmentation for Cross-domain Few-shot Classification](https://mlsanity.com/paper/2208.11021/) (2022)
- [Universal Representations: A Unified Look at Multiple Task and Domain Learning](https://mlsanity.com/paper/2204.02744/) (2022)
- [AMU-Tuning: Effective Logit Bias for CLIP-based Few-shot Learning](https://mlsanity.com/paper/2404.08958/) (2024)
- [Context-Aware Meta-Learning](https://mlsanity.com/paper/2310.10971/) (2023)
- [Reliable Few-shot Learning under Dual Noises](https://mlsanity.com/paper/2506.16330/) (2025)
- [DETA: Denoised Task Adaptation for Few-Shot Learning](https://mlsanity.com/paper/2303.06315/) (2023)
- [CAD: Co-Adapting Discriminative Features for Improved Few-Shot Classification](https://mlsanity.com/paper/2203.13465/) (2022)
- [GeNIe: Generative Hard Negative Images Through Diffusion](https://mlsanity.com/paper/2312.02548/) (2023)
- [Transductive Decoupled Variational Inference for Few-Shot Classification](https://mlsanity.com/paper/2208.10559/) (2022)
- [Discriminative Sample-Guided and Parameter-Efficient Feature Space Adaptation for Cross-Domain Few-Shot Learning](https://mlsanity.com/paper/2403.04492/) (2024)
- [BECLR: Batch Enhanced Contrastive Few-Shot Learning](https://mlsanity.com/paper/2402.02444/) (2024)
- [Beyond Simple Meta-Learning: Multi-Purpose Models for Multi-Domain, Active and Continual Few-Shot Learning](https://mlsanity.com/paper/2201.05151/) (2022)
- [Self-Attention Message Passing for Contrastive Few-Shot Learning](https://mlsanity.com/paper/2210.06339/) (2022)
- [Enhancing Few-shot Image Classification with Cosine Transformer](https://mlsanity.com/paper/2211.06828/) (2022)
- [Meta-tuning Loss Functions and Data Augmentation for Few-shot Object Detection](https://mlsanity.com/paper/2304.12161/) (2023)
- [Meta-DM: Applications of Diffusion Models on Few-Shot Learning](https://mlsanity.com/paper/2305.08092/) (2023)
- [Neural Fine-Tuning Search for Few-Shot Learning](https://mlsanity.com/paper/2306.09295/) (2023)
- [Adaptive Parametric Prototype Learning for Cross-Domain Few-Shot Classification](https://mlsanity.com/paper/2309.01342/) (2023)
- [Feature Extractor Stacking for Cross-domain Few-shot Learning](https://mlsanity.com/paper/2205.05831/) (2022)
- [A Statistical Model for Predicting Generalization in Few-Shot Classification](https://mlsanity.com/paper/2212.06461/) (2022)
- [Dual-View Data Hallucination with Semantic Relation Guidance for Few-Shot Image Recognition](https://mlsanity.com/paper/2401.07061/) (2024)
- [Tiny models from tiny data: Textual and null-text inversion for few-shot distillation](https://mlsanity.com/paper/2406.03146/) (2024)
- [Transductive One-Shot Learning Meet Subspace Decomposition](https://mlsanity.com/paper/2504.00348/) (2025)
- [FAD: Frequency Adaptation and Diversion for Cross-domain Few-shot Learning](https://mlsanity.com/paper/2505.08349/) (2025)
- [Class-Specific Channel Attention for Few-Shot Learning](https://mlsanity.com/paper/2209.01332/) (2022)
- [Few-shot Image Classification based on Gradual Machine Learning](https://mlsanity.com/paper/2307.15524/) (2023)
- [Flatness Improves Backbone Generalisation in Few-shot Classification](https://mlsanity.com/paper/2404.07696/) (2024)

## Abstract (arXiv)

We develop a transductive meta-learning method that uses unlabelled instances to improve few-shot image classification performance. Our approach combines a regularized Mahalanobis-distance-based soft k-means clustering procedure with a modified state of the art neural adaptive feature extractor to achieve improved test-time classification accuracy using unlabelled data. We evaluate our method on transductive few-shot learning tasks, in which the goal is to jointly predict labels for query (test) examples given a set of support (training) examples. We achieve state of the art performance on the Meta-Dataset, mini-ImageNet and tiered-ImageNet benchmarks. All trained models and code have been made publicly available at github.com/plai-group/simple-cnaps.