arXiv:2606. 17020v1 Announce Type: cross Abstract: Remote sensing vision-language models have advanced Earth observation understanding, but most existing work remains centered on RGB imagery, leaving the complementary information in infrared data underexplored.
By Jiaju Han, Ben Zhang, Xuemeng Sun, Qike Zhang, Yuxian Dong, Chengyin Hu, Fengyu Zhang, Yiwei Wei, Jiujiang Guo
Visible-infrared person re-identification (VI-ReID) suffers from cross-modal discrepancies and limited discriminative capabilities, leading to suboptimal recognition performance. Current approaches ex...
Remote sensing vision-language models have advanced Earth observation understanding, but most existing work remains centered on RGB imagery, leaving the complementary information in infrared data underexplored. Infrared images provide distinctive cues, including thermal intensity structures, object boundaries, and illumination-invariant scene features, which can enrich visual-language learning beyond conventional RGB observations.
The paper introduces Aligned Consensus Teacher (ACT), a semi‑supervised framework for visible‑infrared object detection that operates under an image‑pair‑level setting with only a few labeled pairs. ACT combines Cycle‑Consistent Region Alignment, Cross‑Modal Consensus Mean‑Teacher, and Text‑Guided Cross‑Modal Instance Augmentation to address limited supervision, pseudo‑label errors, and scarce tail‑class annotations. Experiments on DroneVehicle and VEDAI demonstrate that with just 10% labeled pairs, ACT achieves 94.3% of the fully supervised mAP.
By Qi Ming, Xiaxin Yuan, Jiahuan Zhou, Jiangmeng Li, Xudong Zhao, Zhanchao Huang, Juan Fang, Shaoguang Huang, Aleksandra Pizurica
S$^3$Geo introduces a structure‑semantic synergistic learning framework for cross‑view geo‑localization, combining a Decoupled Query Pooling module to capture local structural patterns, an optimal‑transport based contrastive learning scheme for soft cross‑view correspondences, and a Semantic Knowledge Distillation strategy from a frozen CLIP teacher to embed semantic priors. The method jointly models fine‑grained structural and semantic information, enabling robust matching between images from vastly different viewpoints such as drone and satellite views. Experiments on University‑1652 and SUES‑200 datasets show that S$^3$Geo outperforms state‑of‑the‑art approaches without increasing inference complexity.
By Ziqian Mo, Hill Zhang, Haosheng Tan, Ling Li, Jiaheng Wei
The paper introduces NWPU-Refer, the largest bilingual dataset for referring remote sensing image segmentation, featuring 15,003 high‑resolution images from over 30 countries and 49,745 annotated targets. It also proposes the Multi‑scale Referring Segmentation Network (MRSNet), which uses an Intra‑scale Feature Interaction Module to refine fine‑grained features and a Hierarchical Feature Interaction Module to fuse cross‑scale information while preserving spatial structure. Experiments on NWPU‑Refer and RRSIS‑D show that MRSNet achieves strong, competitive performance, especially under strict IoU thresholds, demonstrating the effectiveness of both the new dataset and the model.
By Zhigang Yang, Huiguang Yao, Linmao Tian, Xuezhi Zhao, Qiang Li, Qi Wang