Bridging Vision and Language Encoders: Parameter-Efficient Tuning for Referring Image Segmentation

Zunnan Xu, Zhihong Chen, Yong Zhang, Yibing Song, Xiang Wan +1 more
2/14/2026

No official code found. Best implementation: kkakkkka/ETRIS (138 stars, MIT, last commit 2025-06-26).

Abstract

Parameter Efficient Tuning (PET) has gained attention for reducing the number of parameters while maintaining performance and providing better hardware resource savings, but few studies investigate dense prediction tasks and interaction between modalities. In this paper, we do an investigation of efficient tuning problems on referring image segmentation. We propose a novel adapter called Bridger to facilitate cross-modal information exchange and inject task-specific information into the pre-trained model. We also design a lightweight decoder for image segmentation. Our approach achieves comparable or superior performance with only 1.61% to 3.38% backbone parameter updates, evaluated on challenging benchmarks. The code is available at https://github.com/kkakkkka/ETRIS.

View on arXivView PDF

Code Implementations(1)

kkakkkka/ETRISCommunity100%
MIT

[ICCV-2023] The official code of Bridging Vision and Language Encoders: Parameter-Efficient Tuning for Referring Image Segmentation

1386Shell, PythonMar 14, 20231 years agoMIT
deep-learningdeep-neural-networksmachine-learning-algorithmsmulti-modal-fusionmulti-modal-learning+2 more

Similar Papers

HARIS: Human-Like Attention for Reference Image Segmentation

86% match2024

Parameter Efficient Fine-Tuning via Cross Block Orchestration for Segment Anything Model

83% match1 repo122026

Stable Segment Anything Model

83% match1 repo742026

Prompt-Driven Referring Image Segmentation with Instance Contrasting

83% match2026

CAT-SAM: Conditional Tuning for Few-Shot Adaptation of Segment Anything Model

83% match1 repo1382026

Keep the Balance: A Parameter-Efficient Symmetrical Framework for RGB+X Semantic Segmentation

83% match1 repo212026

Cite this paper

@article{xu2026bridging,
  title  = {Bridging Vision and Language Encoders: Parameter-Efficient Tuning for Referring Image Segmentation},
  author = {Zunnan Xu and Zhihong Chen and Yong Zhang and Yibing Song and Xiang Wan and Guanbin Li},
  year   = {2026},
  eprint = {2307.11545},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2307.11545},
  journal = {ICCV 2023 2023}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2307.11545.svg)](https://codeofpaper.com/paper/2307.11545)

Discussion