# SCNet: Enhancing Few-Shot Semantic Segmentation by Self-Contrastive Background Prototypes

arXiv: https://arxiv.org/abs/2104.09216 · HTML: https://mlsanity.com/paper/2104.09216/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 27 references that are in the map.
- First posted on arXiv 19 Apr 2021.

## Builds on (most cited first, 21 of 21)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition](https://mlsanity.com/paper/1406.4729/) (2014)
- [Self-labelling via simultaneous clustering and representation learning](https://mlsanity.com/paper/1911.05371/) (2019)
- [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)
- [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)
- [AET vs. AED: Unsupervised Representation Learning by Auto-Encoding Transformations rather than Data](https://mlsanity.com/paper/1901.04596/) (2019)
- [CliqueCNN: Deep Unsupervised Exemplar Learning](https://mlsanity.com/paper/1608.08792/) (2016)
- [SimPropNet: Improved Similarity Propagation for Few-shot Image Segmentation](https://mlsanity.com/paper/2004.15014/) (2020)

## Built on by (most cited first, 4 of 4)

- [Semi-Supervised Semantic Segmentation with Cross Teacher Training](https://mlsanity.com/paper/2209.01327/) (2022)
- [Generalized Few-Shot Semantic Segmentation: All You Need is Fine-Tuning](https://mlsanity.com/paper/2112.10982/) (2021)
- [Unsupervised Contrastive Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2204.08399/) (2022)
- [Stronger is not better: Better Augmentations in Contrastive Learning for Medical Image Segmentation](https://mlsanity.com/paper/2512.05992/) (2025)

## Abstract (arXiv)

Few-shot semantic segmentation aims to segment novel-class objects in a query image with only a few annotated examples in support images. Most of advanced solutions exploit a metric learning framework that performs segmentation through matching each pixel to a learned foreground prototype. However, this framework suffers from biased classification due to incomplete construction of sample pairs with the foreground prototype only. To address this issue, in this paper, we introduce a complementary self-contrastive task into few-shot semantic segmentation. Our new model is able to associate the pixels in a region with the prototype of this region, no matter they are in the foreground or background. To this end, we generate self-contrastive background prototypes directly from the query image, with which we enable the construction of complete sample pairs and thus a complementary and auxiliary segmentation task to achieve the training of a better segmentation model. Extensive experiments on PASCAL-5i and COCO-20i demonstrate clearly the superiority of our proposal. At no expense of inference efficiency, our model achieves state-of-the results in both 1-shot and 5-shot settings for few-shot semantic segmentation.