# Self-Supervised Tuning for Few-Shot Segmentation

arXiv: https://arxiv.org/abs/2004.05538 · HTML: https://mlsanity.com/paper/2004.05538/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Apr 2020.

## Built on by (most cited first, 17 of 17)

- [Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2107.08918/) (2021)
- [Self-Support Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2207.11549/) (2022)
- [Self-Guided and Cross-Guided Learning for Few-Shot Segmentation](https://mlsanity.com/paper/2103.16129/) (2021)
- [One-Shot Object Affordance Detection in the Wild](https://mlsanity.com/paper/2108.03658/) (2021)
- [PFENet++: Boosting Few-shot Semantic Segmentation with the Noise-filtered Context-aware Prior Mask](https://mlsanity.com/paper/2109.13788/) (2021)
- [Learning Visual Affordance Grounding from Demonstration Videos](https://mlsanity.com/paper/2108.05675/) (2021)
- [Anti-aliasing Semantic Reconstruction for Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2106.00184/) (2021)
- [Learning Expressive Prompting With Residuals for Vision Transformers](https://mlsanity.com/paper/2303.15591/) (2023)
- [From Denoising Training to Test-Time Adaptation: Enhancing Domain Generalization for Medical Image Segmentation](https://mlsanity.com/paper/2310.20271/) (2023)
- [Phrase-Based Affordance Detection via Cyclic Bilateral Interaction](https://mlsanity.com/paper/2202.12076/) (2022)
- [Harmonizing Base and Novel Classes: A Class-Contrastive Approach for Generalized Few-Shot Segmentation](https://mlsanity.com/paper/2303.13724/) (2023)
- [MaskSplit: Self-supervised Meta-learning for Few-shot Semantic Segmentation](https://mlsanity.com/paper/2110.12207/) (2021)
- [Correlation Weighted Prototype-based Self-Supervised One-Shot Segmentation of Medical Images](https://mlsanity.com/paper/2408.06235/) (2024)
- [Unbiased Semantic Decoding with Vision Foundation Models for Few-shot Segmentation](https://mlsanity.com/paper/2511.15118/) (2025)
- [Progressively Dual Prior Guided Few-shot Semantic Segmentation](https://mlsanity.com/paper/2211.15467/) (2022)
- [ISAR: A Benchmark for Single- and Few-Shot Object Instance Segmentation and Re-Identification](https://mlsanity.com/paper/2311.02734/) (2023)
- [Beyond Visual Cues: Leveraging General Semantics as Support for Few-Shot Segmentation](https://mlsanity.com/paper/2511.16435/) (2025)

## Abstract (arXiv)

Few-shot segmentation aims at assigning a category label to each image pixel with few annotated samples. It is a challenging task since the dense prediction can only be achieved under the guidance of latent features defined by sparse annotations. Existing meta-learning method tends to fail in generating category-specifically discriminative descriptor when the visual features extracted from support images are marginalized in embedding space. To address this issue, this paper presents an adaptive tuning framework, in which the distribution of latent features across different episodes is dynamically adjusted based on a self-segmentation scheme, augmenting category-specific descriptors for label prediction. Specifically, a novel self-supervised inner-loop is firstly devised as the base learner to extract the underlying semantic features from the support image. Then, gradient maps are calculated by back-propagating self-supervised loss through the obtained features, and leveraged as guidance for augmenting the corresponding elements in embedding space. Finally, with the ability to continuously learn from different episodes, an optimization-based meta-learner is adopted as outer loop of our proposed framework to gradually refine the segmentation results. Extensive experiments on benchmark PASCAL-5i and COCO-20i datasets demonstrate the superiority of our proposed method over state-of-the-art.