# DARA: Domain- and Relation-aware Adapters Make Parameter-efficient Tuning for Visual Grounding

arXiv: https://arxiv.org/abs/2405.06217 · HTML: https://mlsanity.com/paper/2405.06217/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 24 references that are in the map.
- First posted on arXiv 10 May 2024.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Modeling Context in Referring Expressions](https://mlsanity.com/paper/1608.00272/) (2016)
- [Generation and Comprehension of Unambiguous Object Descriptions](https://mlsanity.com/paper/1511.02283/) (2015)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)
- [MAttNet: Modular Attention Network for Referring Expression Comprehension](https://mlsanity.com/paper/1801.08186/) (2018)
- [TransVG: End-to-End Visual Grounding with Transformers](https://mlsanity.com/paper/2104.08541/) (2021)
- [A Fast and Accurate One-Stage Approach to Visual Grounding](https://mlsanity.com/paper/1908.06354/) (2019)
- [Learning to Compose and Reason with Language Tree Structures for Visual Grounding](https://mlsanity.com/paper/1906.01784/) (2019)
- [Bridging Vision and Language Encoders: Parameter-Efficient Tuning for Referring Image Segmentation](https://mlsanity.com/paper/2307.11545/) (2023)
- [Visual Grounding with Transformers](https://mlsanity.com/paper/2105.04281/) (2021)
- [MmAP : Multi-modal Alignment Prompt for Cross-domain Multi-task Learning](https://mlsanity.com/paper/2312.08636/) (2023)
- [VoP: Text-Video Co-operative Prompt Tuning for Cross-Modal Retrieval](https://mlsanity.com/paper/2211.12764/) (2022)
- [Cross-Modal Adapter for Vision-Language Retrieval](https://mlsanity.com/paper/2211.09623/) (2022)
- [Parameter-Efficient Transfer Learning for Remote Sensing Image-Text Retrieval](https://mlsanity.com/paper/2308.12509/) (2023)
- [VGDiffZero: Text-to-image Diffusion Models Can Be Zero-shot Visual Grounders](https://mlsanity.com/paper/2309.01141/) (2023)
- [DAP: Domain-aware Prompt Learning for Vision-and-Language Navigation](https://mlsanity.com/paper/2311.17812/) (2023)
- [One for All: One-stage Referring Expression Comprehension with Dynamic Reasoning](https://mlsanity.com/paper/2208.00361/) (2022)

## Built on by (most cited first, 5 of 5)

- [Sparse-Tuning: Adapting Vision Transformers with Efficient Fine-tuning and Inference](https://mlsanity.com/paper/2405.14700/) (2024)
- [PropVG: End-to-End Proposal-Driven Visual Grounding with Multi-Granularity Discrimination](https://mlsanity.com/paper/2509.04833/) (2025)
- [SwimVG: Step-wise Multimodal Fusion and Adaption for Visual Grounding](https://mlsanity.com/paper/2502.16786/) (2025)
- [MaPPER: Multimodal Prior-guided Parameter Efficient Tuning for Referring Expression Comprehension](https://mlsanity.com/paper/2409.13609/) (2024)
- [Minimal Interaction Separated Tuning: A New Paradigm for Visual Adaptation](https://mlsanity.com/paper/2406.17559/) (2024)

## Abstract (arXiv)

Visual grounding (VG) is a challenging task to localize an object in an image based on a textual description. Recent surge in the scale of VG models has substantially improved performance, but also introduced a significant burden on computational costs during fine-tuning. In this paper, we explore applying parameter-efficient transfer learning (PETL) to efficiently transfer the pre-trained vision-language knowledge to VG. Specifically, we propose DARA, a novel PETL method comprising underlineDomain-aware underlineAdapters (DA Adapters) and underlineRelation-aware underlineAdapters (RA Adapters) for VG. DA Adapters first transfer intra-modality representations to be more fine-grained for the VG domain. Then RA Adapters share weights to bridge the relation between two modalities, improving spatial reasoning. Empirical results on widely-used benchmarks demonstrate that DARA achieves the best accuracy while saving numerous updated parameters compared to the full fine-tuning and other PETL methods. Notably, with only 2.13% tunable backbone parameters, DARA improves average accuracy by 0.81% across the three benchmarks compared to the baseline model. Our code is available at urlhttps://github.com/liuting20/DARA.