# SimPropNet: Improved Similarity Propagation for Few-shot Image Segmentation

arXiv: https://arxiv.org/abs/2004.15014 · HTML: https://mlsanity.com/paper/2004.15014/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Apr 2020.

## Built on by (most cited first, 27 of 27)

- [Adaptive Prototype Learning and Allocation for Few-Shot Segmentation](https://mlsanity.com/paper/2104.01893/) (2021)
- [Hypercorrelation Squeeze for Few-Shot Segmentation](https://mlsanity.com/paper/2104.01538/) (2021)
- [Efficient and Explicit Modelling of Image Hierarchies for Image Restoration](https://mlsanity.com/paper/2303.00748/) (2023)
- [Self-Support Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2207.11549/) (2022)
- [Self-Guided and Cross-Guided Learning for Few-Shot Segmentation](https://mlsanity.com/paper/2103.16129/) (2021)
- [Hierarchical Dense Correlation Distillation for Few-Shot Segmentation](https://mlsanity.com/paper/2303.14652/) (2023)
- [Feature-Proxy Transformer for Few-Shot Segmentation](https://mlsanity.com/paper/2210.06908/) (2022)
- [Learning Meta-class Memory for Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2108.02958/) (2021)
- [Integrative Few-Shot Learning for Classification and Segmentation](https://mlsanity.com/paper/2203.15712/) (2022)
- [Anti-aliasing Semantic Reconstruction for Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2106.00184/) (2021)
- [Learning Expressive Prompting With Residuals for Vision Transformers](https://mlsanity.com/paper/2303.15591/) (2023)
- [Not All Data Are Unlearned Equally](https://mlsanity.com/paper/2504.05058/) (2025)
- [APANet: Adaptive Prototypes Alignment Network for Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2111.12263/) (2021)
- [A Pixel-Level Meta-Learner for Weakly Supervised Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2111.01418/) (2021)
- [Generalized Few-Shot Semantic Segmentation: All You Need is Fine-Tuning](https://mlsanity.com/paper/2112.10982/) (2021)
- [Harmonizing Base and Novel Classes: A Class-Contrastive Approach for Generalized Few-Shot Segmentation](https://mlsanity.com/paper/2303.13724/) (2023)
- [A Self-Distillation Embedded Supervised Affinity Attention Model for Few-Shot Segmentation](https://mlsanity.com/paper/2108.06600/) (2021)
- [MetaMedSeg: Volumetric Meta-learning for Few-Shot Organ Segmentation](https://mlsanity.com/paper/2109.09734/) (2021)
- [Uncertainty-Aware Semi-Supervised Few Shot Segmentation](https://mlsanity.com/paper/2110.08954/) (2021)
- [SCNet: Enhancing Few-Shot Semantic Segmentation by Self-Contrastive Background Prototypes](https://mlsanity.com/paper/2104.09216/) (2021)
- [End-to-end One-shot Human Parsing](https://mlsanity.com/paper/2105.01241/) (2021)
- [Dual Prototypical Contrastive Learning for Few-shot Semantic Segmentation](https://mlsanity.com/paper/2111.04982/) (2021)
- [Few Shot Semantic Segmentation: a review of methodologies, benchmarks, and open challenges](https://mlsanity.com/paper/2304.05832/) (2023)
- [ATD: Improved Transformer with Adaptive Token Dictionary for Image Restoration](https://mlsanity.com/paper/2603.02581/) (2026)
- [Prior-Enhanced Few-Shot Segmentation with Meta-Prototypes](https://mlsanity.com/paper/2106.00572/) (2021)
- [Hierarchical Dense Correlation Distillation for Few-Shot Segmentation-Extended Abstract](https://mlsanity.com/paper/2306.15278/) (2023)
- [Prototype Learning-Based Few-Shot Segmentation for Low-Light Crack on Concrete Structures](https://mlsanity.com/paper/2601.13059/) (2026)

## Abstract (arXiv)

Few-shot segmentation (FSS) methods perform image segmentation for a particular object class in a target (query) image, using a small set of (support) image-mask pairs. Recent deep neural network based FSS methods leverage high-dimensional feature similarity between the foreground features of the support images and the query image features. In this work, we demonstrate gaps in the utilization of this similarity information in existing methods, and present a framework - SimPropNet, to bridge those gaps. We propose to jointly predict the support and query masks to force the support features to share characteristics with the query features. We also propose to utilize similarities in the background regions of the query and support images using a novel foreground-background attentive fusion mechanism. Our method achieves state-of-the-art results for one-shot and five-shot segmentation on the PASCAL-5i dataset. The paper includes detailed analysis and ablation studies for the proposed improvements and quantitative comparisons with contemporary methods.