# Training-Free Generalized Few-Shot Segmentation through Open-Vocabulary Semantic Arbitration

arXiv: https://arxiv.org/abs/2606.09474 · HTML: https://mlsanity.com/paper/2606.09474/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 34 of its 40 references that are in the map.
- First posted on arXiv 8 Jun 2026.

## Builds on (most cited first, 30 of 34)

- [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)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [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)
- [Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP](https://mlsanity.com/paper/2210.04150/) (2022)
- [PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment](https://mlsanity.com/paper/1908.06391/) (2019)
- [Side Adapter Network for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2302.12242/) (2023)
- [Prior Guided Feature Enrichment Network for Few-Shot Segmentation](https://mlsanity.com/paper/2008.01449/) (2020)
- [A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model](https://mlsanity.com/paper/2112.14757/) (2021)
- [CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2303.11797/) (2023)
- [SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2211.14813/) (2022)
- [Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching](https://mlsanity.com/paper/2305.13310/) (2023)
- [Open-Vocabulary Universal Image Segmentation with MaskCLIP](https://mlsanity.com/paper/2208.08984/) (2022)
- [Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs](https://mlsanity.com/paper/2212.00785/) (2022)
- [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)
- [Open Vocabulary Scene Parsing](https://mlsanity.com/paper/1703.08769/) (2017)
- [VRP-SAM: SAM with Visual Reference Prompt](https://mlsanity.com/paper/2402.17726/) (2024)
- [Generalized Few-shot Semantic Segmentation](https://mlsanity.com/paper/2010.05210/) (2020)
- [Feature-Proxy Transformer for Few-Shot Segmentation](https://mlsanity.com/paper/2210.06908/) (2022)
- [Training-Free Open-Vocabulary Segmentation with Offline Diffusion-Augmented Prototype Generation](https://mlsanity.com/paper/2404.06542/) (2024)
- [Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2210.06780/) (2022)
- [Self-Calibrated Cross Attention Network for Few-Shot Segmentation](https://mlsanity.com/paper/2308.09294/) (2023)
- [LPOSS: Label Propagation Over Patches and Pixels for Open-vocabulary Semantic Segmentation](https://mlsanity.com/paper/2503.19777/) (2025)
- [Visual Prompting for Generalized Few-shot Segmentation: A Multi-scale Approach](https://mlsanity.com/paper/2404.11732/) (2024)
- [Focus on Query: Adversarial Mining Transformer for Few-Shot Segmentation](https://mlsanity.com/paper/2311.17626/) (2023)
- [Unlocking the Power of SAM 2 for Few-Shot Segmentation](https://mlsanity.com/paper/2505.14100/) (2025)

## Abstract (arXiv)

Generalized Few-Shot Semantic Segmentation (GFSS) has traditionally been approached as a representation-learning problem, requiring task-specific adaptation to incorporate novel classes from limited support examples. Recent foundation models, however, already exhibit strong open-vocabulary recognition and segmentation capabilities, raising a different question: can GFSS be solved through inference-time coordination of frozen semantic priors rather than parameter adaptation? We answer this question with Open-V, a training-free GFSS framework that combines Segment Anything (SAM3) Promptable Concept Segmentation (PCS) with a K-shot CLIP support centroid through calibrated per-pixel semantic arbitration. OpenV introduces no trainable components and supports arbitrary semantic categories at inference time. Beyond segmentation performance, our study contributes three broader findings. First, we show that support information can be incorporated through inference-time semantic grounding, and that its contribution increases as foundation-model text priors weaken on label-disjoint vocabularies. Second, we identify a reproducibility confound in foundationmodel segmentation, demonstrating that preprocessing and evaluation-space mismatches can silently distort reported performance. Finally, we validate Open-V across PASCAL5i, COCO-20i, and ADE-OW, showing that training-free coordination of foundation-model priors generalizes across both conventional GFSS and open-vocabulary evaluation settings. On PASCAL-5i (1-shot), Open-V attains base/novel/harmonic mIoU of 78.4/77.5/77.9, without GFSS-specific training surpassing the strongest trained baseline by +17.7 HM.