Metric-Guided Feature Fusion of Visual Foundation Models for Segmentation Tasks

• URL: http://arxiv.org/abs/2605.16864v1
• Date: Sat, 16 May 2026 07:55:41 GMT
• Title: Metric-Guided Feature Fusion of Visual Foundation Models for Segmentation Tasks
• Abstract summary: Large-scale visual foundation models (VFMs) still underperform in instance-aware dense prediction tasks.<n>We propose a metric-guided approach that effectively selects and aggregates complementary features from different VFMs.<n>Our model shows consistent performance gains across multiple dense prediction tasks compared with the baselines.
• Score: 5.5299638491215495
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Although large-scale visual foundation models (VFMs) achieve remarkable performance in semantic understanding, they still underperform in instance-aware dense prediction tasks. They exhibit different biases in representation: for instance, promptable segmentation models (e.g., SAM2) focus on fine-grained region boundaries, while self-supervised models (e.g., DINOv3) emphasize object-level structure. This observation highlights the potential of combining complementary features from different VFMs to enhance downstream dense prediction tasks. However, naive multi-VFM fusion seldom leads to reliable gains, and interpretable principles for leveraging their complementary features are still underexplored. In this work, we propose a metric-guided approach that effectively selects and aggregates complementary features from different VFMs based on explicit assessment scores. Specifically, we design a suite of label-free metrics in feature space across two aspects, Structural Coherence and Edge Fidelity, to assess features of VFM encoders. Guided by these scores, we identify complementary edge-strong and structure-strong encoder pairs, and integrate them via a master-auxiliary fusion scheme. This feature fusion requires no complex architectural changes and is trained only in a single stage. Our model shows consistent performance gains across multiple dense prediction tasks compared with the baselines, with better object-level semantics and more accurately localized boundaries. The code is available at {https://github.com/gyc-code/metric-guided-fusion}.

Related papers

• Semantic Generative Tuning for Unified Multimodal Models [62.18894352635965]
  Unified multimodal models (UMMs) strive to consolidate visual understanding and visual generation within a single architecture.<n> prevailing training paradigms independently optimize understanding via sparse text signals and generation through dense pixel objectives.<n>This work presents the first systematic investigation into generative post-training, where we formulate hierarchical visual tasks as generative proxies to bridge the isolation in UMMs.
  arXiv  Detail & Related papers  (2026-05-18T17:46:46Z)
• INSID3: Training-Free In-Context Segmentation with DINOv3 [63.961377087673476]
  INSID3 is a training-free approach that segments concepts at varying granularities only from frozen DINOv3 features.<n>It achieves state-of-the-art results across one-shot semantic, part, and personalized segmentation, outperforming previous work by +7.5 % mIoU.
  arXiv  Detail & Related papers  (2026-03-30T14:16:37Z)
• DiveUp: Learning Feature Upsampling from Diverse Vision Foundation Models [11.659303031631723]
  DiveUp is a novel framework that breaks away from single-model dependency by introducing multi-VFM relational guidance.<n>We propose a universal relational feature representation, formulated as a local center-of-mass (COM) field, that extracts intrinsic geometric structures.<n>DiveUp is a unified, encoder-agnostic framework; a jointly-trained model can universally upsample features from diverse VFMs.
  arXiv  Detail & Related papers  (2026-03-13T20:20:22Z)
• 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)
• Toward Stable Semi-Supervised Remote Sensing Segmentation via Co-Guidance and Co-Fusion [31.189038928192648]
  Co2S is a semi-supervised RS segmentation framework that fuses priors from vision-language models and self-supervised models.<n>An explicit-implicit semantic co-guidance mechanism is introduced that utilizes text embeddings and learnable queries.<n>Experiments on six popular datasets demonstrate the superiority of the proposed method.
  arXiv  Detail & Related papers  (2025-12-28T18:24:19Z)
• Rethinking Infrared Small Target Detection: A Foundation-Driven Efficient Paradigm [17.63632082331749]
  Large-scale visual foundation models (VFMs) exhibit strong generalization across diverse visual domains, but their potential for single-frame infrared small target (SIRST) detection remains largely unexplored.<n>We propose a Foundation-Driven Efficient Paradigm (FDEP) which can seamlessly adapt to existing encoder-decoder-based methods and significantly improve accuracy without additional inference overhead.
  arXiv  Detail & Related papers  (2025-12-05T08:12:35Z)
• Matching-Based Few-Shot Semantic Segmentation Models Are Interpretable by Design [8.993770750003673]
  Few-Shot Semantic (FSS) models achieve strong performance in segmenting novel classes with minimal labeled examples.<n>This paper introduces the first dedicated method for interpreting matching-based FSS models.<n>Our Affinity Explainer approach extracts attribution maps that highlight which pixels in support images contribute most to query segmentation predictions.
  arXiv  Detail & Related papers  (2025-11-22T19:22:10Z)
• Semi-supervised Semantic Segmentation with Multi-Constraint Consistency Learning [81.02648336552421]
  We propose a Multi-Constraint Consistency Learning approach to facilitate the staged enhancement of the encoder and decoder.<n>Self-adaptive feature masking and noise injection are designed in an instance-specific manner to perturb the features for robust learning of the decoder.<n> Experimental results on Pascal VOC2012 and Cityscapes datasets demonstrate that our proposed MCCL achieves new state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-03-23T03:21:33Z)
• RGM: A Robust Generalizable Matching Model [49.60975442871967]
  We propose a deep model for sparse and dense matching, termed RGM (Robust Generalist Matching) To narrow the gap between synthetic training samples and real-world scenarios, we build a new, large-scale dataset with sparse correspondence ground truth. We are able to mix up various dense and sparse matching datasets, significantly improving the training diversity.
  arXiv  Detail & Related papers  (2023-10-18T07:30:08Z)
• Object Segmentation by Mining Cross-Modal Semantics [68.88086621181628]
  We propose a novel approach by mining the Cross-Modal Semantics to guide the fusion and decoding of multimodal features. Specifically, we propose a novel network, termed XMSNet, consisting of (1) all-round attentive fusion (AF), (2) coarse-to-fine decoder (CFD), and (3) cross-layer self-supervision.
  arXiv  Detail & Related papers  (2023-05-17T14:30:11Z)
• Semantic-aligned Fusion Transformer for One-shot Object Detection [18.58772037047498]
  One-shot object detection aims at detecting novel objects according to merely one given instance. Current approaches explore various feature fusions to obtain directly transferable meta-knowledge. We propose a simple but effective architecture named Semantic-aligned Fusion Transformer (SaFT) to resolve these issues.
  arXiv  Detail & Related papers  (2022-03-17T05:38:47Z)
• MGA-VQA: Multi-Granularity Alignment for Visual Question Answering [75.55108621064726]
  Learning to answer visual questions is a challenging task since the multi-modal inputs are within two feature spaces. We propose Multi-Granularity Alignment architecture for Visual Question Answering task (MGA-VQA) Our model splits alignment into different levels to achieve learning better correlations without needing additional data and annotations.
  arXiv  Detail & Related papers  (2022-01-25T22:30:54Z)

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.