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

arXiv: https://arxiv.org/abs/2605.16864 · HTML: https://mlsanity.com/paper/2605.16864/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 36 of its 43 references that are in the map.
- First posted on arXiv 16 May 2026.

## Builds on (most cited first, 30 of 36)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (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)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [Vision Transformer Adapter for Dense Predictions](https://mlsanity.com/paper/2205.08534/) (2022)
- [Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP](https://mlsanity.com/paper/2210.04150/) (2022)
- [Intriguing Properties of Vision Transformers](https://mlsanity.com/paper/2105.10497/) (2021)
- [Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation](https://mlsanity.com/paper/2206.02777/) (2022)
- [Semantic-SAM: Segment and Recognize Anything at Any Granularity](https://mlsanity.com/paper/2307.04767/) (2023)
- [Probing the 3D Awareness of Visual Foundation Models](https://mlsanity.com/paper/2404.08636/) (2024)
- [AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into One](https://mlsanity.com/paper/2312.06709/) (2023)
- [SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding](https://mlsanity.com/paper/2310.15308/) (2023)
- [CLIP-DINOiser: Teaching CLIP a few DINO tricks for open-vocabulary semantic segmentation](https://mlsanity.com/paper/2312.12359/) (2023)
- [RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models](https://mlsanity.com/paper/2412.07679/) (2024)
- [Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation](https://mlsanity.com/paper/2312.04265/) (2023)
- [Improving Vision Transformers by Revisiting High-frequency Components](https://mlsanity.com/paper/2204.00993/) (2022)
- [Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactively](https://mlsanity.com/paper/2401.02955/) (2024)
- [OMG-Seg: Is One Model Good Enough For All Segmentation?](https://mlsanity.com/paper/2401.10229/) (2024)
- [GiT: Towards Generalist Vision Transformer through Universal Language Interface](https://mlsanity.com/paper/2403.09394/) (2024)
- [Region-Based Representations Revisited](https://mlsanity.com/paper/2402.02352/) (2024)
- [Semantic-aware SAM for Point-Prompted Instance Segmentation](https://mlsanity.com/paper/2312.15895/) (2023)

## Abstract (arXiv)

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}.