# Few-shot Semantic Segmentation with Self-supervision from Pseudo-classes

arXiv: https://arxiv.org/abs/2110.11742 · HTML: https://mlsanity.com/paper/2110.11742/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 34 references that are in the map.
- First posted on arXiv 22 Oct 2021.

## Builds on (most cited first, 20 of 20)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Holistically-Nested Edge Detection](https://mlsanity.com/paper/1504.06375/) (2015)
- [PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment](https://mlsanity.com/paper/1908.06391/) (2019)
- [One-Shot Learning for Semantic Segmentation](https://mlsanity.com/paper/1709.03410/) (2017)
- [Prior Guided Feature Enrichment Network for Few-Shot Segmentation](https://mlsanity.com/paper/2008.01449/) (2020)
- [CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning](https://mlsanity.com/paper/1903.02351/) (2019)
- [Adaptive Prototype Learning and Allocation for Few-Shot Segmentation](https://mlsanity.com/paper/2104.01893/) (2021)
- [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)
- [Simultaneous Detection and Segmentation](https://mlsanity.com/paper/1407.1808/) (2014)
- [Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?](https://mlsanity.com/paper/2012.06166/) (2020)
- [Self-Supervision with Superpixels: Training Few-shot Medical Image Segmentation without Annotation](https://mlsanity.com/paper/2007.09886/) (2020)
- [CRNet: Cross-Reference Networks for Few-Shot Segmentation](https://mlsanity.com/paper/2003.10658/) (2020)
- [SegSort: Segmentation by Discriminative Sorting of Segments](https://mlsanity.com/paper/1910.06962/) (2019)
- [Self-Guided and Cross-Guided Learning for Few-Shot Segmentation](https://mlsanity.com/paper/2103.16129/) (2021)

## Built on by (most cited first, 6 of 6)

- [RestNet: Boosting Cross-Domain Few-Shot Segmentation with Residual Transformation Network](https://mlsanity.com/paper/2308.13469/) (2023)
- [Prototypical few-shot segmentation for cross-institution male pelvic structures with spatial registration](https://mlsanity.com/paper/2209.05160/) (2022)
- [Iterative Few-shot Semantic Segmentation from Image Label Text](https://mlsanity.com/paper/2303.05646/) (2023)
- [Few Shot Semantic Segmentation: a review of methodologies, benchmarks, and open challenges](https://mlsanity.com/paper/2304.05832/) (2023)
- [Unsupervised Learning of Object-Centric Embeddings for Cell Instance Segmentation in Microscopy Images](https://mlsanity.com/paper/2310.08501/) (2023)
- [Online pseudo labeling for polyp segmentation with momentum networks](https://mlsanity.com/paper/2209.14599/) (2022)

## Abstract (arXiv)

Despite the success of deep learning methods for semantic segmentation, few-shot semantic segmentation remains a challenging task due to the limited training data and the generalisation requirement for unseen classes. While recent progress has been particularly encouraging, we discover that existing methods tend to have poor performance in terms of meanIoU when query images contain other semantic classes besides the target class. To address this issue, we propose a novel self-supervised task that generates random pseudo-classes in the background of the query images, providing extra training data that would otherwise be unavailable when predicting individual target classes. To that end, we adopted superpixel segmentation for generating the pseudo-classes. With this extra supervision, we improved the meanIoU performance of the state-of-the-art method by 2.5% and 5.1% on the one-shot tasks, as well as 6.7% and 4.4% on the five-shot tasks, on the PASCAL-5i and COCO benchmarks, respectively.