# OptiSAR-Net++: A Large-Scale Benchmark and Transformer-Free Framework for Cross-Domain Remote Sensing Visual Grounding

arXiv: https://arxiv.org/abs/2603.24876 · HTML: https://mlsanity.com/paper/2603.24876/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Vision mixture-of-experts, one of 12 directions in Mixture-of-experts.
- Builds on 27 of its 60 references that are in the map.
- First posted on arXiv 25 Mar 2026.

## Placed in

- Mixture-of-experts / [Vision mixture-of-experts](https://mlsanity.com/moe/vision-mixture-of-experts/)

## Builds on (most cited first, 27 of 27)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [YOLO-World: Real-Time Open-Vocabulary Object Detection](https://mlsanity.com/paper/2401.17270/) (2024)
- [CSPNet: A New Backbone that can Enhance Learning Capability of CNN](https://mlsanity.com/paper/1911.11929/) (2019)
- [RemoteCLIP: A Vision Language Foundation Model for Remote Sensing](https://mlsanity.com/paper/2306.11029/) (2023)
- [Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free](https://mlsanity.com/paper/2505.06708/) (2025)
- [TransVG: End-to-End Visual Grounding with Transformers](https://mlsanity.com/paper/2104.08541/) (2021)
- [SpectralGPT: Spectral Remote Sensing Foundation Model](https://mlsanity.com/paper/2311.07113/) (2023)
- [A Fast and Accurate One-Stage Approach to Visual Grounding](https://mlsanity.com/paper/1908.06354/) (2019)
- [EarthGPT: A Universal Multi-modal Large Language Model for Multi-sensor Image Comprehension in Remote Sensing Domain](https://mlsanity.com/paper/2401.16822/) (2024)
- [Improving One-stage Visual Grounding by Recursive Sub-query Construction](https://mlsanity.com/paper/2008.01059/) (2020)
- [RSVG: Exploring Data and Models for Visual Grounding on Remote Sensing Data](https://mlsanity.com/paper/2210.12634/) (2022)
- [SkyEyeGPT: Unifying Remote Sensing Vision-Language Tasks via Instruction Tuning with Large Language Model](https://mlsanity.com/paper/2401.09712/) (2024)
- [A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applications](https://mlsanity.com/paper/2503.07137/) (2025)
- [Zero-Shot Grounding of Objects from Natural Language Queries](https://mlsanity.com/paper/1908.07129/) (2019)
- [Cross-City Matters: A Multimodal Remote Sensing Benchmark Dataset for Cross-City Semantic Segmentation using High-Resolution Domain Adaptation Networks](https://mlsanity.com/paper/2309.16499/) (2023)
- [Shifting More Attention to Visual Backbone: Query-modulated Refinement Networks for End-to-End Visual Grounding](https://mlsanity.com/paper/2203.15442/) (2022)
- [Look Before You Leap: Learning Landmark Features for One-Stage Visual Grounding](https://mlsanity.com/paper/2104.04386/) (2021)
- [CrossEarth: Geospatial Vision Foundation Model for Domain Generalizable Remote Sensing Semantic Segmentation](https://mlsanity.com/paper/2410.22629/) (2024)
- [SM3Det: A Unified Model for Multi-Modal Remote Sensing Object Detection](https://mlsanity.com/paper/2412.20665/) (2024)
- [MobileCLIP2: Improving Multi-Modal Reinforced Training](https://mlsanity.com/paper/2508.20691/) (2025)
- [M4-SAR: A Multi-Resolution, Multi-Polarization, Multi-Scene, Multi-Source Dataset and Benchmark for optical-SAR Object Detection](https://mlsanity.com/paper/2505.10931/) (2025)
- [MIFNet: Learning Modality-Invariant Features for Generalizable Multimodal Image Matching](https://mlsanity.com/paper/2501.11299/) (2025)

## Abstract (arXiv)

Remote sensing visual grounding (RSVG) aims to localize specific targets in remote sensing images using natural language expressions. However, existing methods are restricted to single-sensor domains, i.e., either optical or synthetic aperture radar (SAR), limiting their real-world applicability. In this paper, we introduce the Cross-Domain RSVG (CD-RSVG) task and construct OptSAR-RSVG, the first large-scale benchmark dataset for this setting. To tackle the challenges of cross-domain feature modeling, computational inefficiency, and fine-grained semantic discrimination, we propose OptiSAR-Net++. Our framework features a patch-level Low-Rank Adaptation Mixture of Experts (PL-MoE) for efficient cross-domain feature decoupling. To mitigate the substantial computational overhead of Transformer decoding frameworks, we adopt a CLIP-based contrastive paradigm and further incorporate dynamic adversarial negative sampling, thereby transforming generative regression into an efficient cross-modal matching process. Additionally, a text-guided dual-gate fusion module (TGDF-SSA) and a region-aware auxiliary head are introduced to enhance semantic-visual alignment and spatial modeling. Extensive experiments demonstrate that OptiSAR-Net++ achieves SOTA performance on both OptSAR-RSVG and DIOR-RSVG benchmarks, offering significant advantages in localization accuracy and efficiency. The model and dataset have been made publicly available at https://github.com/JunDong-dev/OptiSAR-Net-PlusPlus.