Controllable-LPMoE: Adapting to Challenging Object Segmentation via Dynamic Local Priors from Mixture-of-Experts

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sun, Yanguang, Lian, Jiawei, Yang, Jian, Luo, Lei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912668392095744
author Sun, Yanguang
Lian, Jiawei
Yang, Jian
Luo, Lei
author_facet Sun, Yanguang
Lian, Jiawei
Yang, Jian
Luo, Lei
contents Large-scale foundation models provide powerful feature representations for downstream object segmentation tasks. However, when adapted to specific tasks through the full-parameter fine-tuning, the enormous parameters being updated often results in significant computational overhead, creating a bottleneck in training efficiency. Although existing methods attempt to fine-tune frozen models by directly embedding trainable prompts, these prompts lack inherent semantic priors, limiting the adaptability of large-scale models. In this paper, we propose a novel dynamic priors-based fine-tuning paradigm with fewer trainable parameters, dubbed Controllable-LPMoE, which adaptively modulates frozen foundation models by dynamically controlling local priors to enhance fine-grained perception for specific segmentation tasks. More specifically, we construct a lightweight dynamic mixed local priors extractor that captures diverse local priors from input images through heterogeneous convolutions while employing a gating network to dynamically output expert priors required for the subsequent fine-tuning. Furthermore, we design a bi-directional interaction adapter that employs cosine-aligned deformable attention and channel-oriented adaptive scale enhancement to interact and restructure between frozen and trainable features, achieving efficient fine-tuning. Extensive experiments validate the superiority of our \href{https://github.com/CSYSI/Controllable-LPMoE} {Controllable-LPMoE} approach, demonstrating excellent segmentation performance compared to 31 state-of-the-art (SOTA) methods and adaptability to multiple binary object segmentation tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2510_21114
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Controllable-LPMoE: Adapting to Challenging Object Segmentation via Dynamic Local Priors from Mixture-of-Experts
Sun, Yanguang
Lian, Jiawei
Yang, Jian
Luo, Lei
Computer Vision and Pattern Recognition
Large-scale foundation models provide powerful feature representations for downstream object segmentation tasks. However, when adapted to specific tasks through the full-parameter fine-tuning, the enormous parameters being updated often results in significant computational overhead, creating a bottleneck in training efficiency. Although existing methods attempt to fine-tune frozen models by directly embedding trainable prompts, these prompts lack inherent semantic priors, limiting the adaptability of large-scale models. In this paper, we propose a novel dynamic priors-based fine-tuning paradigm with fewer trainable parameters, dubbed Controllable-LPMoE, which adaptively modulates frozen foundation models by dynamically controlling local priors to enhance fine-grained perception for specific segmentation tasks. More specifically, we construct a lightweight dynamic mixed local priors extractor that captures diverse local priors from input images through heterogeneous convolutions while employing a gating network to dynamically output expert priors required for the subsequent fine-tuning. Furthermore, we design a bi-directional interaction adapter that employs cosine-aligned deformable attention and channel-oriented adaptive scale enhancement to interact and restructure between frozen and trainable features, achieving efficient fine-tuning. Extensive experiments validate the superiority of our \href{https://github.com/CSYSI/Controllable-LPMoE} {Controllable-LPMoE} approach, demonstrating excellent segmentation performance compared to 31 state-of-the-art (SOTA) methods and adaptability to multiple binary object segmentation tasks.
title Controllable-LPMoE: Adapting to Challenging Object Segmentation via Dynamic Local Priors from Mixture-of-Experts
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.21114