# Prototype-based Incremental Few-Shot Semantic Segmentation

arXiv: https://arxiv.org/abs/2012.01415 · HTML: https://mlsanity.com/paper/2012.01415/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Nov 2020.

## Built on by (most cited first, 25 of 25)

- [Class-Incremental Learning: A Survey](https://mlsanity.com/paper/2302.03648/) (2023)
- [A Survey on Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2304.08130/) (2023)
- [Incremental Learning in Semantic Segmentation from Image Labels](https://mlsanity.com/paper/2112.01882/) (2021)
- [Semantic Image Segmentation: Two Decades of Research](https://mlsanity.com/paper/2302.06378/) (2023)
- [CoMFormer: Continual Learning in Semantic and Panoptic Segmentation](https://mlsanity.com/paper/2211.13999/) (2022)
- [Modeling Missing Annotations for Incremental Learning in Object Detection](https://mlsanity.com/paper/2204.08766/) (2022)
- [A Survey on Continual Semantic Segmentation: Theory, Challenge, Method and Application](https://mlsanity.com/paper/2310.14277/) (2023)
- [Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Model](https://mlsanity.com/paper/2503.16282/) (2025)
- [Incremental Few-Shot Semantic Segmentation via Embedding Adaptive-Update and Hyper-class Representation](https://mlsanity.com/paper/2207.12964/) (2022)
- [Generalized Few-Shot Point Cloud Segmentation Via Geometric Words](https://mlsanity.com/paper/2309.11222/) (2023)
- [Advancing Incremental Few-shot Semantic Segmentation via Semantic-guided Relation Alignment and Adaptation](https://mlsanity.com/paper/2305.10868/) (2023)
- [RaSP: Relation-aware Semantic Prior for Weakly Supervised Incremental Segmentation](https://mlsanity.com/paper/2305.19879/) (2023)
- [Prototypical Kernel Learning and Open-set Foreground Perception for Generalized Few-shot Semantic Segmentation](https://mlsanity.com/paper/2308.04952/) (2023)
- [Learning from Mistakes: Self-Regularizing Hierarchical Representations in Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2301.11145/) (2023)
- [Few Shot Semantic Segmentation: a review of methodologies, benchmarks, and open challenges](https://mlsanity.com/paper/2304.05832/) (2023)
- [ProCNS: Progressive Prototype Calibration and Noise Suppression for Weakly-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2401.14074/) (2024)
- [Organizing Background to Explore Latent Classes for Incremental Few-shot Semantic Segmentation](https://mlsanity.com/paper/2405.19568/) (2024)
- [Swiss DINO: Efficient and Versatile Vision Framework for On-device Personal Object Search](https://mlsanity.com/paper/2407.07541/) (2024)
- [Few-shot Class-Incremental Semantic Segmentation via Pseudo-Labeling and Knowledge Distillation](https://mlsanity.com/paper/2308.02790/) (2023)
- [Show or Tell? A Benchmark To Evaluate Visual and Textual Prompts in Semantic Segmentation](https://mlsanity.com/paper/2505.06280/) (2025)
- [Probabilistic Prototype Calibration of Vision-Language Models for Generalized Few-shot Semantic Segmentation](https://mlsanity.com/paper/2506.22979/) (2025)
- [SCOPE: Scene-Contextualized Incremental Few-Shot 3D Segmentation](https://mlsanity.com/paper/2603.06572/) (2026)
- [Learning Hierarchical Orthogonal Prototypes for Generalized Few-Shot 3D Point Cloud Segmentation](https://mlsanity.com/paper/2603.19788/) (2026)
- [Task Consistent Prototype Learning for Incremental Few-shot Semantic Segmentation](https://mlsanity.com/paper/2410.13094/) (2024)
- [Open-world Point Cloud Semantic Segmentation: A Human-in-the-loop Framework](https://mlsanity.com/paper/2508.04962/) (2025)

## Abstract (arXiv)

Semantic segmentation models have two fundamental weaknesses: i) they require large training sets with costly pixel-level annotations, and ii) they have a static output space, constrained to the classes of the training set. Toward addressing both problems, we introduce a new task, Incremental Few-Shot Segmentation (iFSS). The goal of iFSS is to extend a pretrained segmentation model with new classes from few annotated images and without access to old training data. To overcome the limitations of existing models iniFSS, we propose Prototype-based Incremental Few-Shot Segmentation (PIFS) that couples prototype learning and knowledge distillation. PIFS exploits prototypes to initialize the classifiers of new classes, fine-tuning the network to refine its features representation. We design a prototype-based distillation loss on the scores of both old and new class prototypes to avoid overfitting and forgetting, and batch-renormalization to cope with non-i.i.d.few-shot data. We create an extensive benchmark for iFSS showing that PIFS outperforms several few-shot and incremental learning methods in all scenarios.