Papers
arxiv:2603.13571

DiveUp: Learning Feature Upsampling from Diverse Vision Foundation Models

Published on Mar 13
Authors:
,

Abstract

DiveUp is a novel feature upsampling framework that uses multi-vision foundation model relational guidance with universal feature representation and spikiness-aware selection to improve pixel-level understanding tasks.

AI-generated summary

Recently, feature upsampling has gained increasing attention owing to its effectiveness in enhancing vision foundation models (VFMs) for pixel-level understanding tasks. Existing methods typically rely on high-resolution features from the same foundation model to achieve upsampling via self-reconstruction. However, relying solely on intra-model features forces the upsampler to overfit to the source model's inherent location misalignment and high-norm artifacts. To address this fundamental limitation, we propose DiveUp, a novel framework that breaks away from single-model dependency by introducing multi-VFM relational guidance. Instead of naive feature fusion, DiveUp leverages diverse VFMs as a panel of experts, utilizing their structural consensus to regularize the upsampler's learning process, effectively preventing the propagation of inaccurate spatial structures from the source model. To reconcile the unaligned feature spaces across different VFMs, we propose a universal relational feature representation, formulated as a local center-of-mass (COM) field, that extracts intrinsic geometric structures, enabling seamless cross-model interaction. Furthermore, we introduce a spikiness-aware selection strategy that evaluates the spatial reliability of each VFM, effectively filtering out high-norm artifacts to aggregate guidance from only the most reliable expert at each local region. DiveUp is a unified, encoder-agnostic framework; a jointly-trained model can universally upsample features from diverse VFMs without requiring per-model retraining. Extensive experiments demonstrate that DiveUp achieves state-of-the-art performance across various downstream dense prediction tasks, validating the efficacy of multi-expert relational guidance. Our code and models are available at: https://github.com/Xiaoqiong-Liu/DiveUp

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2603.13571
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2603.13571 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2603.13571 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2603.13571 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.