{"ID":2850445,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.21114","arxiv_id":"2510.21114","title":"Controllable-LPMoE: Adapting to Challenging Object Segmentation via Dynamic Local Priors from Mixture-of-Experts","abstract":"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.","short_abstract":"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 ef...","url_abs":"https://arxiv.org/abs/2510.21114","url_pdf":"https://arxiv.org/pdf/2510.21114v1","authors":"[\"Yanguang Sun\",\"Jiawei Lian\",\"Jian Yang\",\"Lei Luo\"]","published":"2025-10-24T03:03:59Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":607802,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2850445,"paper_url":"https://arxiv.org/abs/2510.21114","paper_title":"Controllable-LPMoE: Adapting to Challenging Object Segmentation via Dynamic Local Priors from Mixture-of-Experts","repo_url":"https://github.com/CSYSI/Controllable-LPMoE","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}