Metraipolis › archive › dc_1aaa25baaaf6

Aligned Consensus Teaching for Label-Efficient Oriented Object Detection in Weakly-Aligned Visible-Infrared Imagery — arXiv:2609.18124

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.18124
License (as archived)
CC0-1.0
Archived
2026-10-15T16:16:19.960Z
SHA-256 of the archived text
db6ce0493459497cfb5f707c08623e2490d1ff4a9227332154af121d7e8a74a2
Stable URL of this page
https://metraipolis.com/documento/dc_1aaa25baaaf6

How to cite

Aligned Consensus Teaching for Label-Efficient Oriented Object Detection in Weakly-Aligned Visible-Infrared Imagery — arXiv:2609.18124 — arXiv (en), https://arxiv.org/abs/2609.18124 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1aaa25baaaf6 (Metraipolis archive dc_1aaa25baaaf6, sha256 db6ce0493459497cfb5f707c08623e2490d1ff4a9227332154af121d7e8a74a2)
BibTeX
@misc{dc1aaa25baaaf6,
  title = {Aligned Consensus Teaching for Label-Efficient Oriented Object Detection in Weakly-Aligned Visible-Infrared Imagery — arXiv:2609.18124},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.18124},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1aaa25baaaf6; sha256 db6ce0493459497cfb5f707c08623e2490d1ff4a9227332154af121d7e8a74a2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.18124. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Visible-infrared object detection (VIOD) detects objects with oriented bounding boxes from paired visible and infrared images. Existing methods depend on costly dual-modality annotations. Semi-supervised learning can reduce this burden, but extending it from single-modal detection to VIOD is challenging. In the practical image-pair-level setting considered here, only a few pairs are labeled in both modalities, while the rest are completely unlabeled. This limited supervision creates three challenges: (i) too few labeled boxes for robust cross-modal alignment; (ii) pseudo-label errors caused by branch-wise misses accumulate during self-training; and (iii) tail-class annotations become critically scarce as the labeling budget decreases. We propose Aligned Consensus Teacher (ACT) for label-efficient VIOD in this setting. Its Cycle-Consistent Region Alignment (CRA) combines cycle consistency and sparse anchors with reliability-weighted regional matching. Cross-Modal Consensus Mean-Teacher (CMC-MT) forms consensus pseudo labels under pair-preserving views to recover branch-wise misses and supervise unlabeled pairs. Text-Guided Cross-Modal Instance Augmentation (TG-CMIA) uses a vision-language scene prior to compose tail-class instance pairs while preserving RGB--IR offsets. To the best of our knowledge, ACT is the first framework to study semi-supervised VIOD under this image-pair-level setting. Experiments on DroneVehicle and VEDAI show consistent gains across annotation ratios. With 10\% labeled pairs on DroneVehicle, ACT reaches 94.3\% of the mAP obtained by the same detector under full supervision. Code and models will be available on GitHub to facilitate future work.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-17 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.18124 — 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 2026-10-15T15:45:19.747Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).