Metraipolis › archive › dc_e6927ec28ec7

A2DINOv3: Rethinking Multi-Modal Object Detection via Socialized Collaboration — arXiv:2608.21099

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.21099
License (as archived)
CC0-1.0
Archived
2026-10-18T10:56:19.055Z
SHA-256 of the archived text
1392340a59b95af5f800c5ee21915d8e65ae0c970e564af31f5bb1f6ba6fd483
Stable URL of this page
https://metraipolis.com/documento/dc_e6927ec28ec7

How to cite

A2DINOv3: Rethinking Multi-Modal Object Detection via Socialized Collaboration — arXiv:2608.21099 — arXiv (en), https://arxiv.org/abs/2608.21099 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e6927ec28ec7 (Metraipolis archive dc_e6927ec28ec7, sha256 1392340a59b95af5f800c5ee21915d8e65ae0c970e564af31f5bb1f6ba6fd483)
BibTeX
@misc{dce6927ec28ec7,
  title = {A2DINOv3: Rethinking Multi-Modal Object Detection via Socialized Collaboration — arXiv:2608.21099},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.21099},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e6927ec28ec7; sha256 1392340a59b95af5f800c5ee21915d8e65ae0c970e564af31f5bb1f6ba6fd483},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.21099. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-24 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.21099 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T10:48:13.596Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).