Unify the Views: View-Consistent Prototype Learning for Few-Shot Segmentation

• URL: http://arxiv.org/abs/2603.05952v1
• Date: Fri, 06 Mar 2026 06:36:42 GMT
• Title: Unify the Views: View-Consistent Prototype Learning for Few-Shot Segmentation
• Abstract summary: Few-shot segmentation (FSS) has gained significant attention for its ability to generalize to novel classes with limited supervision.<n>This paper tackles these challenges by introducing VINE, a unified framework that models structural consistency and discrimination to refine class-specific prototypes.
• Score: 23.546777614096424
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• When Features Become Instances: Inverted Contrastive Learning for Unsupervised Feature Selection [0.0]
  Unsupervised feature selection seeks a compact subset of informative features without access to class labels.<n>We propose Inverted Contrastive Learning for Unsupervised Feature Selection (ICLFS)<n>ICLFS reformulates UFS as a representation learning problem over features rather than samples.
  arXiv  Detail & Related papers  (2026-09-01T06:25:43Z)
• DAS-PMVC: A Framework for Partial Multi-View Clustering via Dual Alignment and Structure Enhancement [13.05750989297313]
  This paper proposes a framework for partial multi-view clustering via dual alignment and structure enhancement (DAS-PMVC)<n>DAS-PMVC includes three parts: textbfanchor graph structure alignment, textbfstructure-enhanced feature learning, and textbfa dual alignment strategy<n> Experimental results on various datasets demonstrate that the DAS-PMVC framework outperforms existing state-of-the-art methods in clustering performance.
  arXiv  Detail & Related papers  (2026-07-30T07:01:35Z)
• SPORT: Structure-Aware Prototype Disentanglement for Incomplete Multi-View Clustering [51.01038967474103]
  Prototype-based Incomplete Multi-view Clustering has attracted increasing attention by exploiting prototypes as semantic anchors for missing-view imputation.<n>We propose a novel framework termed Structure-aware PrOtotype disentanglement foR incomplete multi-view clusTering (SPORT)<n>SPORT explicitly disentangles shared and view-specific components of prototypes while preserving cluster-level relational structures.
  arXiv  Detail & Related papers  (2026-07-11T17:40:22Z)
• Learning Cross-View Semantic Priors for Single-Reference Unseen Object Pose Estimation [18.011730388391232]
  We build a correspondence pipeline around an early cross-view semantic prior.<n>Our method achieves state-of-the-art performance while maintaining comparable inference speed.
  arXiv  Detail & Related papers  (2026-06-20T14:50:51Z)
• SAMatcher: Co-Visibility Modeling with Segment Anything for Robust Feature Matching [25.84764820920445]
  We propose SAMatcher, a feature matching framework that formulates correspondence estimation through co-visibility modeling.<n>It introduces a symmetric cross-view interaction mechanism that enables bidirectional feature exchange and cross-view semantic alignment.<n>Our results show that foundation models originally designed for monocular segmentation can be effectively extended to multi-view correspondence reasoning.
  arXiv  Detail & Related papers  (2026-06-02T09:47:59Z)
• Hierarchical Consistency Learning for Test-time Adaptation in Camouflage Perception [50.278200968044665]
  Camouflaged object detection (COD) aims to localize targets that exhibit minimal perceptual differences from backgrounds through physical attributes.<n>Existing methods, constrained by the static train-then-freeze paradigm, suffer from domain rigidity and dependency annotation.<n>We propose the hierarchical consistency learning framework, which integrates test-time adaptation for dynamic representation recalibration.
  arXiv  Detail & Related papers  (2026-05-25T09:57:46Z)
• HAAF: Hierarchical Adaptation and Alignment of Foundation Models for Few-Shot Pathology Anomaly Detection [10.649984141835189]
  We propose the Hierarchical Adaptation and Alignment Framework (HAAF)<n>At its core is a novel Cross-Level Scaled Alignment mechanism that enforces a sequential calibration order.<n>A dual-branch inference strategy integrates semantic scores with geometric prototypes to ensure stability in few-shot settings.
  arXiv  Detail & Related papers  (2026-01-24T10:31:21Z)
• MS-ISSM: Objective Quality Assessment of Point Clouds Using Multi-scale Implicit Structural Similarity [65.85858856481131]
  unstructured and irregular nature of point clouds poses a significant challenge for objective quality assessment (PCQA)<n>We propose the Multi-scale Implicit Structural Similarity Measurement (MS-ISSM)
  arXiv  Detail & Related papers  (2026-01-03T14:58:52Z)
• ConStruct: Structural Distillation of Foundation Models for Prototype-Based Weakly Supervised Histopathology Segmentation [16.733170895296343]
  Weakly supervised semantic segmentation (WSSS) in histopathology relies heavily on classification backbones.<n>We propose a prototype learning framework that integrates morphology-aware representations from CONCH, multi-scale structural cues from SegFormer, and text-guided semantic alignment.<n>Our approach produces high-quality pseudo masks without pixel-level annotations, improves localization completeness, and enhances semantic consistency across tissue types.
  arXiv  Detail & Related papers  (2025-12-11T06:08:29Z)
• Generalized Decoupled Learning for Enhancing Open-Vocabulary Dense Perception [71.26728044621458]
  DeCLIP is a novel framework that enhances CLIP by decoupling the self-attention module to obtain content'' and context'' features respectively.<n>It consistently achieves state-of-the-art performance across a broad spectrum of tasks, including 2D detection and segmentation, 3D instance segmentation, video instance segmentation, and 6D object pose estimation.
  arXiv  Detail & Related papers  (2025-08-15T06:43:51Z)
• "Principal Components" Enable A New Language of Images [79.45806370905775]
  We introduce a novel visual tokenization framework that embeds a provable PCA-like structure into the latent token space.<n>Our approach achieves state-of-the-art reconstruction performance and enables better interpretability to align with the human vision system.
  arXiv  Detail & Related papers  (2025-03-11T17:59:41Z)
• Learning and Evaluating Hierarchical Feature Representations [3.770103075126785]
  We propose a novel framework, Hierarchical Composition of Orthogonal Subspaces (Hier-COS)<n>Hier-COS learns to map deep feature embeddings into a vector space that is, by design, consistent with the structure of a given taxonomy tree.<n>We demonstrate that Hier-COS achieves state-of-the-art hierarchical performance across all the datasets while simultaneously beating top-1 accuracy in all but one case.
  arXiv  Detail & Related papers  (2025-03-10T20:59:41Z)
• Beyond Mask: Rethinking Guidance Types in Few-shot Segmentation [67.35274834837064]
  We develop a universal vision-language framework (UniFSS) to integrate prompts from text, mask, box, and image. UniFSS significantly outperforms the state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-07-16T08:41:01Z)
• Structure-Aware Feature Generation for Zero-Shot Learning [108.76968151682621]
  We introduce a novel structure-aware feature generation scheme, termed as SA-GAN, to account for the topological structure in learning both the latent space and the generative networks. Our method significantly enhances the generalization capability on unseen-classes and consequently improve the classification performance.
  arXiv  Detail & Related papers  (2021-08-16T11:52:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.