人工智能
分割
计算机科学
计算机视觉
特征(语言学)
模式识别(心理学)
基础(证据)
图像分割
融合
特征提取
可视化
传感器融合
图像融合
作者
Guo Yachan,Jose L. Gómez,Danna Xue,Yi Xiao,Antonio Manuel López
标识
DOI:10.1109/cvprf71909.2026.00314
摘要
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 selfsupervised 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.
科研通智能强力驱动
Strongly Powered by AbleSci AI