# A Two-Stage Approach to Few-Shot Learning for Image Recognition

arXiv: https://arxiv.org/abs/1912.04973 · HTML: https://mlsanity.com/paper/1912.04973/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Dec 2019.

## Built on by (most cited first, 18 of 18)

- [FeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learning](https://mlsanity.com/paper/2211.13131/) (2022)
- [Deep Metric Learning for Few-Shot Image Classification: A Review of Recent Developments](https://mlsanity.com/paper/2105.08149/) (2021)
- [Alleviating the Sample Selection Bias in Few-shot Learning by Removing Projection to the Centroid](https://mlsanity.com/paper/2210.16834/) (2022)
- [A Closer Look at Prototype Classifier for Few-shot Image Classification](https://mlsanity.com/paper/2110.05076/) (2021)
- [Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning](https://mlsanity.com/paper/2110.09446/) (2021)
- [Multi-level Metric Learning for Few-shot Image Recognition](https://mlsanity.com/paper/2103.11383/) (2021)
- [Prototype Completion for Few-Shot Learning](https://mlsanity.com/paper/2108.05010/) (2021)
- [Semi-Supervised Disease Classification based on Limited Medical Image Data](https://mlsanity.com/paper/2405.04295/) (2024)
- [Dizygotic Conditional Variational AutoEncoder for Multi-Modal and Partial Modality Absent Few-Shot Learning](https://mlsanity.com/paper/2106.14467/) (2021)
- [Compensation Learning](https://mlsanity.com/paper/2107.11921/) (2021)
- [Few-shot Classification with Hypersphere Modeling of Prototypes](https://mlsanity.com/paper/2211.05319/) (2022)
- [NAS-TC: Neural Architecture Search on Temporal Convolutions for Complex Action Recognition](https://mlsanity.com/paper/2104.01110/) (2021)
- [Task Attended Meta-Learning for Few-Shot Learning](https://mlsanity.com/paper/2106.10642/) (2021)
- [Dual-View Data Hallucination with Semantic Relation Guidance for Few-Shot Image Recognition](https://mlsanity.com/paper/2401.07061/) (2024)
- [Not All Instances Contribute Equally: Instance-adaptive Class Representation Learning for Few-Shot Visual Recognition](https://mlsanity.com/paper/2209.03034/) (2022)
- [Activating the Discriminability of Novel Classes for Few-shot Segmentation](https://mlsanity.com/paper/2212.01131/) (2022)
- [Video-to-Task Learning via Motion-Guided Attention for Few-Shot Action Recognition](https://mlsanity.com/paper/2411.11335/) (2024)
- [A Comprehensive Survey of Challenges and Opportunities of Few-Shot Learning Across Multiple Domains](https://mlsanity.com/paper/2504.04017/) (2025)

## Abstract (arXiv)

This paper proposes a multi-layer neural network structure for few-shot image recognition of novel categories. The proposed multi-layer neural network architecture encodes transferable knowledge extracted from a large annotated dataset of base categories. This architecture is then applied to novel categories containing only a few samples. The transfer of knowledge is carried out at the feature-extraction and the classification levels distributed across the two training stages. In the first-training stage, we introduce the relative feature to capture the structure of the data as well as obtain a low-dimensional discriminative space. Secondly, we account for the variable variance of different categories by using a network to predict the variance of each class. Classification is then performed by computing the Mahalanobis distance to the mean-class representation in contrast to previous approaches that used the Euclidean distance. In the second-training stage, a category-agnostic mapping is learned from the mean-sample representation to its corresponding class-prototype representation. This is because the mean-sample representation may not accurately represent the novel category prototype. Finally, we evaluate the proposed network structure on four standard few-shot image recognition datasets, where our proposed few-shot learning system produces competitive performance compared to previous work. We also extensively studied and analyzed the contribution of each component of our proposed framework.