# Self-Regularized Prototypical Network for Few-Shot Semantic Segmentation

arXiv: https://arxiv.org/abs/2210.16829 · HTML: https://mlsanity.com/paper/2210.16829/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 61 references that are in the map.
- First posted on arXiv 30 Oct 2022.

## Builds on (most cited first, 30 of 39)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment](https://mlsanity.com/paper/1908.06391/) (2019)
- [TADAM: Task dependent adaptive metric for improved few-shot learning](https://mlsanity.com/paper/1805.10123/) (2018)
- [Recent Advances in Convolutional Neural Networks](https://mlsanity.com/paper/1512.07108/) (2015)
- [One-Shot Learning for Semantic Segmentation](https://mlsanity.com/paper/1709.03410/) (2017)
- [Few-Shot Learning with Graph Neural Networks](https://mlsanity.com/paper/1711.04043/) (2017)
- [Prior Guided Feature Enrichment Network for Few-Shot Segmentation](https://mlsanity.com/paper/2008.01449/) (2020)
- [Vision-Language Transformer and Query Generation for Referring Segmentation](https://mlsanity.com/paper/2108.05565/) (2021)
- [CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning](https://mlsanity.com/paper/1903.02351/) (2019)
- [Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning](https://mlsanity.com/paper/1805.10002/) (2018)
- [Prototype Mixture Models for Few-shot Semantic Segmentation](https://mlsanity.com/paper/2008.03898/) (2020)
- [Feature Weighting and Boosting for Few-Shot Segmentation](https://mlsanity.com/paper/1909.13140/) (2019)
- [SG-One: Similarity Guidance Network for One-Shot Semantic Segmentation](https://mlsanity.com/paper/1810.09091/) (2018)
- [Part-aware Prototype Network for Few-shot Semantic Segmentation](https://mlsanity.com/paper/2007.06309/) (2020)
- [MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesis](https://mlsanity.com/paper/2103.14910/) (2021)
- [VLT: Vision-Language Transformer and Query Generation for Referring Segmentation](https://mlsanity.com/paper/2210.15871/) (2022)
- [Boundary-Aware Feature Propagation for Scene Segmentation](https://mlsanity.com/paper/1909.00179/) (2019)
- [CRNet: Cross-Reference Networks for Few-Shot Segmentation](https://mlsanity.com/paper/2003.10658/) (2020)
- [Prototype Rectification for Few-Shot Learning](https://mlsanity.com/paper/1911.10713/) (2019)
- [Recovering the Unbiased Scene Graphs from the Biased Ones](https://mlsanity.com/paper/2107.02112/) (2021)
- [Semantic Correlation Promoted Shape-Variant Context for Segmentation](https://mlsanity.com/paper/1909.02651/) (2019)
- [FGN: Fully Guided Network for Few-Shot Instance Segmentation](https://mlsanity.com/paper/2003.13954/) (2020)
- [Instance-Specific Feature Propagation for Referring Segmentation](https://mlsanity.com/paper/2204.12109/) (2022)
- [Few-shot Segmentation with Optimal Transport Matching and Message Flow](https://mlsanity.com/paper/2108.08518/) (2021)

## Built on by (most cited first, 12 of 12)

- [Towards Open Vocabulary Learning: A Survey](https://mlsanity.com/paper/2306.15880/) (2023)
- [Prototype Adaption and Projection for Few- and Zero-shot 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2305.14335/) (2023)
- [Rethinking Prior Information Generation with CLIP for Few-Shot Segmentation](https://mlsanity.com/paper/2405.08458/) (2024)
- [GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning](https://mlsanity.com/paper/2304.06007/) (2023)
- [MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping](https://mlsanity.com/paper/2409.11316/) (2024)
- [Boosting Few-Shot Semantic Segmentation Via Segment Anything Model](https://mlsanity.com/paper/2401.09826/) (2024)
- [Few-shot 3D LiDAR Semantic Segmentation for Autonomous Driving](https://mlsanity.com/paper/2302.08785/) (2023)
- [Beyond Mask: Rethinking Guidance Types in Few-shot Segmentation](https://mlsanity.com/paper/2407.11503/) (2024)
- [Few-Shot Segmentation of Historical Maps via Linear Probing of Vision Foundation Models](https://mlsanity.com/paper/2506.21826/) (2025)
- [LERENet: Eliminating Intra-class Differences for Metal Surface Defect Few-shot Semantic Segmentation](https://mlsanity.com/paper/2403.11122/) (2024)
- [Matching-Based Few-Shot Semantic Segmentation Models Are Interpretable by Design](https://mlsanity.com/paper/2511.18163/) (2025)
- [DistillFSS: Synthesizing Few-Shot Knowledge into a Lightweight Segmentation Model](https://mlsanity.com/paper/2512.05613/) (2025)

## Abstract (arXiv)

The deep CNNs in image semantic segmentation typically require a large number of densely-annotated images for training and have difficulties in generalizing to unseen object categories. Therefore, few-shot segmentation has been developed to perform segmentation with just a few annotated examples. In this work, we tackle the few-shot segmentation using a self-regularized prototypical network (SRPNet) based on prototype extraction for better utilization of the support information. The proposed SRPNet extracts class-specific prototype representations from support images and generates segmentation masks for query images by a distance metric - the fidelity. A direct yet effective prototype regularization on support set is proposed in SRPNet, in which the generated prototypes are evaluated and regularized on the support set itself. The extent to which the generated prototypes restore the support mask imposes an upper limit on performance. The performance on the query set should never exceed the upper limit no matter how complete the knowledge is generalized from support set to query set. With the specific prototype regularization, SRPNet fully exploits knowledge from the support and offers high-quality prototypes that are representative for each semantic class and meanwhile discriminative for different classes. The query performance is further improved by an iterative query inference (IQI) module that combines a set of regularized prototypes. Our proposed SRPNet achieves new state-of-art performance on 1-shot and 5-shot segmentation benchmarks.