# Prototype Completion with Primitive Knowledge for Few-Shot Learning

arXiv: https://arxiv.org/abs/2009.04960 · HTML: https://mlsanity.com/paper/2009.04960/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Sep 2020.

## Built on by (most cited first, 30 of 50)

- [D4M: Dataset Distillation via Disentangled Diffusion Model](https://mlsanity.com/paper/2407.15138/) (2024)
- [MetaDiff: Meta-Learning with Conditional Diffusion for Few-Shot Learning](https://mlsanity.com/paper/2307.16424/) (2023)
- [Generating Representative Samples for Few-Shot Classification](https://mlsanity.com/paper/2205.02918/) (2022)
- [Matching Feature Sets for Few-Shot Image Classification](https://mlsanity.com/paper/2204.00949/) (2022)
- [Task Discrepancy Maximization for Fine-grained Few-Shot Classification](https://mlsanity.com/paper/2207.01376/) (2022)
- [Cross-Modal Prototype based Multimodal Federated Learning under Severely Missing Modality](https://mlsanity.com/paper/2401.13898/) (2024)
- [Alleviating the Sample Selection Bias in Few-shot Learning by Removing Projection to the Centroid](https://mlsanity.com/paper/2210.16834/) (2022)
- [Codebook Transfer with Part-of-Speech for Vector-Quantized Image Modeling](https://mlsanity.com/paper/2403.10071/) (2024)
- [SEGA: Semantic Guided Attention on Visual Prototype for Few-Shot Learning](https://mlsanity.com/paper/2111.04316/) (2021)
- [Simple Semantic-Aided Few-Shot Learning](https://mlsanity.com/paper/2311.18649/) (2023)
- [Multimodal Prototype-Enhanced Network for Few-Shot Action Recognition](https://mlsanity.com/paper/2212.04873/) (2022)
- [MetaNODE: Prototype Optimization as a Neural ODE for Few-Shot Learning](https://mlsanity.com/paper/2103.14341/) (2021)
- [What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data](https://mlsanity.com/paper/2106.06410/) (2021)
- [Connecting Giants: Synergistic Knowledge Transfer of Large Multimodal Models for Few-Shot Learning](https://mlsanity.com/paper/2510.11115/) (2025)
- [Envisioning Class Entity Reasoning by Large Language Models for Few-shot Learning](https://mlsanity.com/paper/2408.12469/) (2024)
- [Prototype Completion for Few-Shot Learning](https://mlsanity.com/paper/2108.05010/) (2021)
- [Transductive Decoupled Variational Inference for Few-Shot Classification](https://mlsanity.com/paper/2208.10559/) (2022)
- [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)
- [Generalized Semantic Contrastive Learning via Embedding Side Information for Few-Shot Object Detection](https://mlsanity.com/paper/2504.07060/) (2025)
- [Progressive Co-Attention Network for Fine-grained Visual Classification](https://mlsanity.com/paper/2101.08527/) (2021)
- [GDC- Generalized Distribution Calibration for Few-Shot Learning](https://mlsanity.com/paper/2204.05230/) (2022)
- [SGMNet: Scene Graph Matching Network for Few-Shot Remote Sensing Scene Classification](https://mlsanity.com/paper/2110.04494/) (2021)
- [Exploring Category-correlated Feature for Few-shot Image Classification](https://mlsanity.com/paper/2112.07224/) (2021)
- [DiffKendall: A Novel Approach for Few-Shot Learning with Differentiable Kendall's Rank Correlation](https://mlsanity.com/paper/2307.15317/) (2023)
- [Task-Oriented Channel Attention for Fine-Grained Few-Shot Classification](https://mlsanity.com/paper/2308.00093/) (2023)
- [Few-shot Partial Multi-view Learning](https://mlsanity.com/paper/2105.02046/) (2021)
- [Few-shot Learning as Cluster-induced Voronoi Diagrams: A Geometric Approach](https://mlsanity.com/paper/2202.02471/) (2022)
- [Rethinking the Metric in Few-shot Learning: From an Adaptive Multi-Distance Perspective](https://mlsanity.com/paper/2211.00890/) (2022)

## Abstract (arXiv)

Few-shot learning is a challenging task, which aims to learn a classifier for novel classes with few examples. Pre-training based meta-learning methods effectively tackle the problem by pre-training a feature extractor and then fine-tuning it through the nearest centroid based meta-learning. However, results show that the fine-tuning step makes very marginal improvements. In this paper, 1) we figure out the key reason, i.e., in the pre-trained feature space, the base classes already form compact clusters while novel classes spread as groups with large variances, which implies that fine-tuning the feature extractor is less meaningful; 2) instead of fine-tuning the feature extractor, we focus on estimating more representative prototypes during meta-learning. Consequently, we propose a novel prototype completion based meta-learning framework. This framework first introduces primitive knowledge (i.e., class-level part or attribute annotations) and extracts representative attribute features as priors. Then, we design a prototype completion network to learn to complete prototypes with these priors. To avoid the prototype completion error caused by primitive knowledge noises or class differences, we further develop a Gaussian based prototype fusion strategy that combines the mean-based and completed prototypes by exploiting the unlabeled samples. Extensive experiments show that our method: (i) can obtain more accurate prototypes; (ii) outperforms state-of-the-art techniques by 2% - 9% in terms of classification accuracy. Our code is available online.