# Few-Shot Semantic Segmentation Meets SAM3

arXiv: https://arxiv.org/abs/2604.05433 · HTML: https://mlsanity.com/paper/2604.05433/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 24 references that are in the map.
- First posted on arXiv 7 Apr 2026.

## Builds on (most cited first, 24 of 24)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [Prior Guided Feature Enrichment Network for Few-Shot Segmentation](https://mlsanity.com/paper/2008.01449/) (2020)
- [Personalize Segment Anything Model with One Shot](https://mlsanity.com/paper/2305.03048/) (2023)
- [Hypercorrelation Squeeze for Few-Shot Segmentation](https://mlsanity.com/paper/2104.01538/) (2021)
- [Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching](https://mlsanity.com/paper/2305.13310/) (2023)
- [Learning What Not to Segment: A New Perspective on Few-Shot Segmentation](https://mlsanity.com/paper/2203.07615/) (2022)
- [Self-Support Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2207.11549/) (2022)
- [Hierarchical Dense Correlation Distillation for Few-Shot Segmentation](https://mlsanity.com/paper/2303.14652/) (2023)
- [VRP-SAM: SAM with Visual Reference Prompt](https://mlsanity.com/paper/2402.17726/) (2024)
- [Feature-Proxy Transformer for Few-Shot Segmentation](https://mlsanity.com/paper/2210.06908/) (2022)
- [Bridge the Points: Graph-based Few-shot Segment Anything Semantically](https://mlsanity.com/paper/2410.06964/) (2024)
- [Self-Calibrated Cross Attention Network for Few-Shot Segmentation](https://mlsanity.com/paper/2308.09294/) (2023)
- [Hybrid Mamba for Few-Shot Segmentation](https://mlsanity.com/paper/2409.19613/) (2024)
- [Eliminating Feature Ambiguity for Few-Shot Segmentation](https://mlsanity.com/paper/2407.09842/) (2024)
- [Focus on Query: Adversarial Mining Transformer for Few-Shot Segmentation](https://mlsanity.com/paper/2311.17626/) (2023)
- [Learning to Prompt Segment Anything Models](https://mlsanity.com/paper/2401.04651/) (2024)
- [Unlocking the Power of SAM 2 for Few-Shot Segmentation](https://mlsanity.com/paper/2505.14100/) (2025)
- [Adaptive FSS: A Novel Few-Shot Segmentation Framework via Prototype Enhancement](https://mlsanity.com/paper/2312.15731/) (2023)
- [SANSA: Unleashing the Hidden Semantics in SAM2 for Few-Shot Segmentation](https://mlsanity.com/paper/2505.21795/) (2025)

## Built on by (most cited first, 3 of 3)

- [Training-Free Generalized Few-Shot Segmentation through Open-Vocabulary Semantic Arbitration](https://mlsanity.com/paper/2606.09474/) (2026)
- [SADe: Sparse-Atom Support Decontamination for Few-Shot Segmentation with Weak Support Annotations](https://mlsanity.com/paper/2607.24706/) (2026)
- [Few-Shot Open-Vocabulary Remote Sensing Segmentation via Textual Inversion](https://mlsanity.com/paper/2607.25563/) (2026)

## Abstract (arXiv)

Few-Shot Semantic Segmentation (FSS) focuses on segmenting novel object categories from only a handful of annotated examples. Most existing approaches rely on extensive episodic training to learn transferable representations, which is both computationally demanding and sensitive to distribution shifts. In this work, we revisit FSS from the perspective of modern vision foundation models and explore the potential of Segment Anything Model 3 (SAM3) as a training-free solution. By repurposing its Promptable Concept Segmentation (PCS) capability, we adopt a simple spatial concatenation strategy that places support and query images into a shared canvas, allowing a fully frozen SAM3 to perform segmentation without any fine-tuning or architectural changes. Experiments on PASCAL-5i and COCO-20i show that this minimal design already achieves state-of-the-art performance, outperforming many heavily engineered methods. Beyond empirical gains, we uncover that negative prompts can be counterproductive in few-shot settings, where they often weaken target representations and lead to prediction collapse despite their intended role in suppressing distractors. These findings suggest that strong cross-image reasoning can emerge from simple spatial formulations, while also highlighting limitations in how current foundation models handle conflicting prompt signals. Code at: https://github.com/WongKinYiu/FSS-SAM3