# Mixture-based Feature Space Learning for Few-shot Image Classification

arXiv: https://arxiv.org/abs/2011.11872 · HTML: https://mlsanity.com/paper/2011.11872/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Nov 2020.

## Built on by (most cited first, 23 of 23)

- [Rethinking Generalization in Few-Shot Classification](https://mlsanity.com/paper/2206.07267/) (2022)
- [Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learning](https://mlsanity.com/paper/2203.09064/) (2022)
- [Matching Feature Sets for Few-Shot Image Classification](https://mlsanity.com/paper/2204.00949/) (2022)
- [Supervised Masked Knowledge Distillation for Few-Shot Transformers](https://mlsanity.com/paper/2303.15466/) (2023)
- [Cross-Domain Video Anomaly Detection without Target Domain Adaptation](https://mlsanity.com/paper/2212.07010/) (2022)
- [Cap2Aug: Caption guided Image to Image data Augmentation](https://mlsanity.com/paper/2212.05404/) (2022)
- [Robust Meta-learning with Sampling Noise and Label Noise via Eigen-Reptile](https://mlsanity.com/paper/2206.01944/) (2022)
- [Mitigating the Effect of Incidental Correlations on Part-based Learning](https://mlsanity.com/paper/2310.00377/) (2023)
- [Worst Case Matters for Few-Shot Recognition](https://mlsanity.com/paper/2203.06574/) (2022)
- [Few-shot Fine-grained Image Classification via Multi-Frequency Neighborhood and Double-cross Modulation](https://mlsanity.com/paper/2207.08547/) (2022)
- [Enhancing Few-Shot Image Classification through Learnable Multi-Scale Embedding and Attention Mechanisms](https://mlsanity.com/paper/2409.07989/) (2024)
- [Dual-View Data Hallucination with Semantic Relation Guidance for Few-Shot Image Recognition](https://mlsanity.com/paper/2401.07061/) (2024)
- [Intra-task Mutual Attention based Vision Transformer for Few-Shot Learning](https://mlsanity.com/paper/2405.03109/) (2024)
- [Class-relevant Patch Embedding Selection for Few-Shot Image Classification](https://mlsanity.com/paper/2405.03722/) (2024)
- [Multi-Level Correlation Network For Few-Shot Image Classification](https://mlsanity.com/paper/2412.03159/) (2024)
- [Frequency-Enhanced Dual-Subspace Networks for Few-Shot Fine-Grained Image Classification](https://mlsanity.com/paper/2604.14958/) (2026)
- [Fine-grained Few-shot Recognition by Deep Object Parsing](https://mlsanity.com/paper/2207.07110/) (2022)
- [FORML: A Riemannian Hessian-free Method for Meta-learning on Stiefel Manifolds](https://mlsanity.com/paper/2402.18605/) (2024)
- [Like Humans to Few-Shot Learning through Knowledge Permeation of Vision and Text](https://mlsanity.com/paper/2405.12543/) (2024)
- [Siamese Transformer Networks for Few-shot Image Classification](https://mlsanity.com/paper/2408.01427/) (2024)
- [Multiple Stochastic Prompt Tuning for Few-shot Adaptation under Extreme Domain Shift](https://mlsanity.com/paper/2506.03926/) (2025)
- [Hierarchical Mask-Enhanced Dual Reconstruction Network for Few-Shot Fine-Grained Image Classification](https://mlsanity.com/paper/2506.20263/) (2025)
- [Shallow Deep Learning Can Still Excel in Fine-Grained Few-Shot Learning](https://mlsanity.com/paper/2507.22041/) (2025)

## Abstract (arXiv)

We introduce Mixture-based Feature Space Learning (MixtFSL) for obtaining a rich and robust feature representation in the context of few-shot image classification. Previous works have proposed to model each base class either with a single point or with a mixture model by relying on offline clustering algorithms. In contrast, we propose to model base classes with mixture models by simultaneously training the feature extractor and learning the mixture model parameters in an online manner. This results in a richer and more discriminative feature space which can be employed to classify novel examples from very few samples. Two main stages are proposed to train the MixtFSL model. First, the multimodal mixtures for each base class and the feature extractor parameters are learned using a combination of two loss functions. Second, the resulting network and mixture models are progressively refined through a leader-follower learning procedure, which uses the current estimate as a "target" network. This target network is used to make a consistent assignment of instances to mixture components, which increases performance and stabilizes training. The effectiveness of our end-to-end feature space learning approach is demonstrated with extensive experiments on four standard datasets and four backbones. Notably, we demonstrate that when we combine our robust representation with recent alignment-based approaches, we achieve new state-of-the-art results in the inductive setting, with an absolute accuracy for 5-shot classification of 82.45 on miniImageNet, 88.20 with tieredImageNet, and 60.70 in FC100 using the ResNet-12 backbone.