# Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation

arXiv: https://arxiv.org/abs/2501.08580 · HTML: https://mlsanity.com/paper/2501.08580/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jan 2025.

## Built on by (most cited first, 26 of 26)

- [FireEdit: Fine-grained Instruction-based Image Editing via Region-aware Vision Language Model](https://mlsanity.com/paper/2503.19839/) (2025)
- [SAM-R1: Leveraging SAM for Reward Feedback in Multimodal Segmentation via Reinforcement Learning](https://mlsanity.com/paper/2505.22596/) (2025)
- [Multimodal Referring Segmentation: A Survey](https://mlsanity.com/paper/2508.00265/) (2025)
- [Intra- and Cross-Scale Feature Interaction Network for Referring Remote Sensing Image Segmentation](https://mlsanity.com/paper/2506.03583/) (2025)
- [PropVG: End-to-End Proposal-Driven Visual Grounding with Multi-Granularity Discrimination](https://mlsanity.com/paper/2509.04833/) (2025)
- [WeakMCN: Multi-task Collaborative Network for Weakly Supervised Referring Expression Comprehension and Segmentation](https://mlsanity.com/paper/2505.18686/) (2025)
- [Stepping Out of Similar Semantic Space for Open-Vocabulary Segmentation](https://mlsanity.com/paper/2506.16058/) (2025)
- [Advancing Visual Large Language Model for Multi-granular Versatile Perception](https://mlsanity.com/paper/2507.16213/) (2025)
- [F-Adapter: Frequency-Adaptive Parameter-Efficient Fine-Tuning in Scientific Machine Learning](https://mlsanity.com/paper/2509.23173/) (2025)
- [SSP-SAM: SAM with Semantic-Spatial Prompt for Referring Expression Segmentation](https://mlsanity.com/paper/2603.18086/) (2026)
- [SetCon: Towards Open-Ended Referring Segmentation via Set-Level Concept Prediction](https://mlsanity.com/paper/2605.20110/) (2026)
- [RIS-LAD: A Benchmark and Model for Referring Low-Altitude Drone Image Segmentation](https://mlsanity.com/paper/2507.20920/) (2025)
- [Layover or Direct Flight: Rethinking Audio-Guided Image Segmentation](https://mlsanity.com/paper/2511.22025/) (2025)
- [TALENT: Target-aware Efficient Tuning for Referring Image Segmentation](https://mlsanity.com/paper/2604.00609/) (2026)
- [Tarot-SAM3: Training-free SAM3 for Any Referring Expression Segmentation](https://mlsanity.com/paper/2604.07916/) (2026)
- [CROSS: Cascaded Distillation and Dual-Constraint Grounding for Remote Sensing Referring Segmentation](https://mlsanity.com/paper/2608.03147/) (2026)
- [TFANet: Three-Stage Image-Text Feature Alignment Network for Robust Referring Image Segmentation](https://mlsanity.com/paper/2509.13070/) (2025)
- [VIPA: Visual Informative Part Attention for Referring Image Segmentation](https://mlsanity.com/paper/2602.14788/) (2026)
- [Spatio-Semantic Expert Routing Architecture with Mixture-of-Experts for Referring Image Segmentation](https://mlsanity.com/paper/2603.12538/) (2026)
- [Towards Motion-aware Referring Image Segmentation](https://mlsanity.com/paper/2603.17413/) (2026)
- [CoLA: Cross-Modal Low-rank Adaptation for Multimodal Downstream Tasks](https://mlsanity.com/paper/2604.03314/) (2026)
- [Channel Attention-Guided Cross-Modal Knowledge Distillation for Referring Image Segmentation](https://mlsanity.com/paper/2604.16806/) (2026)
- [Boosting Text-Driven Video Segmentation via Geometry-Aware Distillation](https://mlsanity.com/paper/2606.24464/) (2026)
- [Semantic-Driven Scale and Spatial Selection for Efficient Cross-Modal Alignment in Referring Remote Sensing Image Segmentation](https://mlsanity.com/paper/2606.30244/) (2026)
- [DeCo: Efficient Decouple-to-Couple Learning for Multi-Task Visual Grounding](https://mlsanity.com/paper/2609.24409/) (2026)
- [0.5%>100%: Bidirectional Reciprocal Learning for Referring Image Segmentation](https://mlsanity.com/paper/2609.24510/) (2026)

## Abstract (arXiv)

In the domain of computer vision, Parameter-Efficient Tuning (PET) is increasingly replacing the traditional paradigm of pre-training followed by full fine-tuning. PET is particularly favored for its effectiveness in large foundation models, as it streamlines transfer learning costs and optimizes hardware utilization. However, the current PET methods are mainly designed for single-modal optimization. While some pioneering studies have undertaken preliminary explorations, they still remain at the level of aligned encoders (e.g., CLIP) and lack exploration of misaligned encoders. These methods show sub-optimal performance with misaligned encoders, as they fail to effectively align the multimodal features during fine-tuning. In this paper, we introduce DETRIS, a parameter-efficient tuning framework designed to enhance low-rank visual feature propagation by establishing dense interconnections between each layer and all preceding layers, which enables effective cross-modal feature interaction and adaptation to misaligned encoders. We also suggest using text adapters to improve textual features. Our simple yet efficient approach greatly surpasses state-of-the-art methods with 0.9% to 1.8% backbone parameter updates, evaluated on challenging benchmarks. Our project is available at urlhttps://github.com/jiaqihuang01/DETRIS.