Unify the Views: View-Consistent Prototype Learning for Few-Shot Segmentation
Not on the map. Why?
Abstract (arXiv)
Few-shot segmentation (FSS) has gained significant attention for its ability to generalize to novel classes with limited supervision, yet remains challenged by structural misalignment and cross-view inconsistency under large appearance or viewpoint variations. This paper tackles these challenges by introducing VINE (View-Informed NEtwork), a unified framework that jointly models structural consistency and foreground discrimination to refine class-specific prototypes. Specifically, VINE introduces a spatial-view graph on backbone features, where the spatial graph captures local geometric topology and the view graph connects features from different perspectives to propagate view-invariant structural semantics. To further alleviate foreground ambiguity, we derive a discriminative prior from the support-query feature discrepancy to capture category-specific contrast, which reweights SAM features by emphasizing salient regions and recalibrates backbone activations for improved structural focus. The foreground-enhanced SAM features and structurally enriched ResNet features are progressively integrated through masked cross-attention, yielding class-consistent prototypes used as adaptive prompts for the SAM decoder to generate accurate masks. Extensive experiments on multiple FSS benchmarks validate the effectiveness and robustness of VINE, particularly under challenging scenarios with viewpoint shifts and complex structures. The code is available at https://github.com/HongliLiu1/VINE-main.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 36 of its 40 references that are in the map. First posted on arXiv 6 Mar 2026.
Builds on
36 of 40 references.
References · 36
- 2014Microsoft COCO: Common Objects in Contextcited by 17,498
- 2017Graph Attention Networkscited by 8,854
- 2023Segment Anythingcited by 8,158
- 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
- 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
- 2021Segmenter: Transformer for Semantic Segmentationcited by 855
- 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
- 2017One-Shot Learning for Semantic Segmentationcited by 337
- 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
- 2019Feature Weighting and Boosting for Few-Shot Segmentationcited by 189
- 2014Simultaneous Detection and Segmentationcited by 158
- 2023Matcher: Segment Anything with One Shot Using All-Purpose Feature Matchingcited by 142
24 more
- 2020Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?cited by 135
- 2021Few-Shot Segmentation via Cycle-Consistent Transformercited by 133
- 2022Learning What Not to Segment: A New Perspective on Few-Shot Segmentationcited by 120
- 2022Self-Support Few-Shot Semantic Segmentationcited by 96
- 2023Hierarchical Dense Correlation Distillation for Few-Shot Segmentationcited by 84
- 2024VRP-SAM: SAM with Visual Reference Promptcited by 75
- 2022Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentationcited by 65
- 2024Bridge the Points: Graph-based Few-shot Segment Anything Semanticallycited by 35
- 2023Self-Calibrated Cross Attention Network for Few-Shot Segmentationcited by 32
- 2024APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentationcited by 26
- 2023FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Networkcited by 22
- 2024Hybrid Mamba for Few-Shot Segmentationcited by 21
- 2023SEGIC: Unleashing the Emergent Correspondence for In-Context Segmentationcited by 19
- 2024Eliminating Feature Ambiguity for Few-Shot Segmentationcited by 19
- 2024A Simple Image Segmentation Framework via In-Context Examplescited by 19
- 2023Adaptive FSS: A Novel Few-Shot Segmentation Framework via Prototype Enhancementcited by 10
- 2024SAM-MPA: Applying SAM to Few-shot Medical Image Segmentation using Mask Propagation and Auto-promptingcited by 9
- 2025Foreground-Covering Prototype Generation and Matching for SAM-Aided Few-Shot Segmentationcited by 9
- 2025Self-Disentanglement and Re-Composition for Cross-Domain Few-Shot Segmentationcited by 9
- 2025The Devil is in Low-Level Features for Cross-Domain Few-Shot Segmentationcited by 8
- 2023Task-Disruptive Background Suppression for Few-Shot Segmentationcited by 7
- 2023Few-shot Semantic Segmentation with Support-induced Graph Convolutional Networkcited by 3
- 2024Beyond Mask: Rethinking Guidance Types in Few-shot Segmentationcited by 3
- 2025Few-shot Structure-Informed Machinery Part Segmentation with Foundation Models and Graph Neural Networkscited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.