# Prototype Refinement Network for Few-Shot Segmentation

arXiv: https://arxiv.org/abs/2002.03579 · HTML: https://mlsanity.com/paper/2002.03579/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Feb 2020.

## Built on by (most cited first, 11 of 11)

- [Learning What Not to Segment: A New Perspective on Few-Shot Segmentation](https://mlsanity.com/paper/2203.07615/) (2022)
- [Hierarchical Dense Correlation Distillation for Few-Shot Segmentation](https://mlsanity.com/paper/2303.14652/) (2023)
- [Few-Shot Medical Image Segmentation via a Region-enhanced Prototypical Transformer](https://mlsanity.com/paper/2309.04825/) (2023)
- [FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Network](https://mlsanity.com/paper/2301.08160/) (2023)
- [MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentation](https://mlsanity.com/paper/2206.09667/) (2022)
- [A Location-Sensitive Local Prototype Network for Few-Shot Medical Image Segmentation](https://mlsanity.com/paper/2103.10178/) (2021)
- [Towards Multi-modality Fusion and Prototype-based Feature Refinement for Clinically Significant Prostate Cancer Classification in Transrectal Ultrasound](https://mlsanity.com/paper/2406.14069/) (2024)
- [Enhancing Generalized Few-Shot Semantic Segmentation via Effective Knowledge Transfer](https://mlsanity.com/paper/2412.15835/) (2024)
- [Prototypical Region Proposal Networks for Few-Shot Localization and Classification](https://mlsanity.com/paper/2104.03496/) (2021)
- [Hierarchical Dense Correlation Distillation for Few-Shot Segmentation-Extended Abstract](https://mlsanity.com/paper/2306.15278/) (2023)
- [Memory-guided Network with Uncertainty-based Feature Augmentation for Few-shot Semantic Segmentation](https://mlsanity.com/paper/2406.00545/) (2024)

## Abstract (arXiv)

Few-shot segmentation targets to segment new classes with few annotated images provided. It is more challenging than traditional semantic segmentation tasks that segment known classes with abundant annotated images. In this paper, we propose a Prototype Refinement Network (PRNet) to attack the challenge of few-shot segmentation. It firstly learns to bidirectionally extract prototypes from both support and query images of the known classes. Furthermore, to extract representative prototypes of the new classes, we use adaptation and fusion for prototype refinement. The step of adaptation makes the model to learn new concepts which is directly implemented by retraining. Prototype fusion is firstly proposed which fuses support prototypes with query prototypes, incorporating the knowledge from both sides. It is effective in prototype refinement without importing extra learnable parameters. In this way, the prototypes become more discriminative in low-data regimes. Experiments on PASAL-5i and COCO-20i demonstrate the superiority of our method. Especially on COCO-20i, PRNet significantly outperforms existing methods by a large margin of 13.1% in 1-shot setting.