# Few-shot Class-Incremental Semantic Segmentation via Pseudo-Labeling and Knowledge Distillation

arXiv: https://arxiv.org/abs/2308.02790 · HTML: https://mlsanity.com/paper/2308.02790/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Detection and dense prediction distillation, one of 12 directions in Knowledge distillation.
- Builds on 14 of its 18 references that are in the map.
- First posted on arXiv 5 Aug 2023.

## Placed in

- Knowledge distillation / [Detection and dense prediction distillation](https://mlsanity.com/distill/detection-and-dense-prediction-distillation/)

## Builds on (most cited first, 14 of 14)

- [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)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2004.10956/) (2020)
- [Part-aware Prototype Network for Few-shot Semantic Segmentation](https://mlsanity.com/paper/2007.06309/) (2020)
- [Augmented Reality Meets Computer Vision : Efficient Data Generation for Urban Driving Scenes](https://mlsanity.com/paper/1708.01566/) (2017)
- [When Does Self-supervision Improve Few-shot Learning?](https://mlsanity.com/paper/1910.03560/) (2019)
- [Incremental Few-Shot Instance Segmentation](https://mlsanity.com/paper/2105.05312/) (2021)
- [Knowledge Distillation for Incremental Learning in Semantic Segmentation](https://mlsanity.com/paper/1911.03462/) (2019)
- [Class-Incremental Learning for Semantic Segmentation Re-Using Neither Old Data Nor Old Labels](https://mlsanity.com/paper/2005.06050/) (2020)
- [Prototype-based Incremental Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2012.01415/) (2020)
- [iFS-RCNN: An Incremental Few-shot Instance Segmenter](https://mlsanity.com/paper/2205.15562/) (2022)
- [Incremental Few-Shot Semantic Segmentation via Embedding Adaptive-Update and Hyper-class Representation](https://mlsanity.com/paper/2207.12964/) (2022)

## Built on by (most cited first, 2 of 2)

- [A Survey on Continual Semantic Segmentation: Theory, Challenge, Method and Application](https://mlsanity.com/paper/2310.14277/) (2023)
- [Evolving Without Ending: Unifying Multimodal Incremental Learning for Continual Panoptic Perception](https://mlsanity.com/paper/2601.15643/) (2026)

## Abstract (arXiv)

We address the problem of learning new classes for semantic segmentation models from few examples, which is challenging because of the following two reasons. Firstly, it is difficult to learn from limited novel data to capture the underlying class distribution. Secondly, it is challenging to retain knowledge for existing classes and to avoid catastrophic forgetting. For learning from limited data, we propose a pseudo-labeling strategy to augment the few-shot training annotations in order to learn novel classes more effectively. Given only one or a few images labeled with the novel classes and a much larger set of unlabeled images, we transfer the knowledge from labeled images to unlabeled images with a coarse-to-fine pseudo-labeling approach in two steps. Specifically, we first match each labeled image to its nearest neighbors in the unlabeled image set at the scene level, in order to obtain images with a similar scene layout. This is followed by obtaining pseudo-labels within this neighborhood by applying classifiers learned on the few-shot annotations. In addition, we use knowledge distillation on both labeled and unlabeled data to retain knowledge on existing classes. We integrate the above steps into a single convolutional neural network with a unified learning objective. Extensive experiments on the Cityscapes and KITTI datasets validate the efficacy of the proposed approach in the self-driving domain. Code is available from https://github.com/ChasonJiang/FSCILSS.