# A2DINOv3: Rethinking Multi-Modal Object Detection via Socialized Collaboration

arXiv: https://arxiv.org/abs/2608.21099 · HTML: https://mlsanity.com/paper/2608.21099/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 30 references that are in the map.
- First posted on arXiv 21 Aug 2026.

## Builds on (most cited first, 17 of 17)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention](https://mlsanity.com/paper/2303.16199/) (2023)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)
- [Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection](https://mlsanity.com/paper/2203.16220/) (2022)
- [LLVIP: A Visible-infrared Paired Dataset for Low-light Vision](https://mlsanity.com/paper/2108.10831/) (2021)
- [Drone-based RGB-Infrared Cross-Modality Vehicle Detection via Uncertainty-Aware Learning](https://mlsanity.com/paper/2003.02437/) (2020)
- [Multispectral Fusion for Object Detection with Cyclic Fuse-and-Refine Blocks](https://mlsanity.com/paper/2009.12664/) (2020)
- [Improving Multispectral Pedestrian Detection by Addressing Modality Imbalance Problems](https://mlsanity.com/paper/2008.03043/) (2020)
- [Dense Distinct Query for End-to-End Object Detection](https://mlsanity.com/paper/2303.12776/) (2023)
- [ICAFusion: Iterative Cross-Attention Guided Feature Fusion for Multispectral Object Detection](https://mlsanity.com/paper/2308.07504/) (2023)
- [RF-DETR: Neural Architecture Search for Real-Time Detection Transformers](https://mlsanity.com/paper/2511.09554/) (2025)
- [Towards Efficient Visual Adaption via Structural Re-parameterization](https://mlsanity.com/paper/2302.08106/) (2023)
- [DEIM: DETR with Improved Matching for Fast Convergence](https://mlsanity.com/paper/2412.04234/) (2024)
- [Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models](https://mlsanity.com/paper/2606.03748/) (2026)
- [Rethinking Multi-Modal Object Detection from the Perspective of Mono-Modality Feature Learning](https://mlsanity.com/paper/2503.11780/) (2025)
- [COXNet: Cross-Layer Fusion with Adaptive Alignment and Scale Integration for RGBT Tiny Object Detection](https://mlsanity.com/paper/2508.09533/) (2025)

## Abstract (arXiv)

Multi-modal object detection is essential for robust scene understanding in challenging conditions, including low-light and adverse environments. Recent vision foundation models (e.g., DINOv3) have exhibited strong representation capabilities, yet adapting them to multi-modal scenarios remains challenging. Existing dense cross-modal fusion strategies often force heterogeneous modalities to interact indiscriminately, which may introduce redundant information and disrupt the valuable pre-trained representations. To address this issue, we revisit multi-modal fusion from the perspective of socialized learning and propose adapter to DINOv3 (A2DINOv3), a multi-expert collaboration framework with a Socialized Collaboration Protocol (SCP). Specifically, RGB and infrared branches are modeled as heterogeneous experts that independently preserve their specialized knowledge while exchanging complementary information through selective and constrained interactions. This design mitigates harmful cross-modal interference and prevents degradation of pre-trained priors during adaptation. Furthermore, a zero-initialization strategy is introduced to gradually activate cross-modal collaboration, enabling a smooth transition from modality-specific learning to cooperative representation learning. Extensive experiments on four multi-modal benchmarks, including aerial detection (GAIIC), autonomous driving (FLIR), low-light surveillance (LLVIP), and diverse real-world scenarios (M3FD), demonstrate that A2DINOv3 consistently achieves state-of-the-art performance in multi-modal object detection.