2 papers
cs.CV2026
One Stone, Three Birds: Self-adaptive Optimal Transport for Multi-VLM Selection, Adaptation, and Ensembling
Qiyu Xu, Zhanxuan Hu, Yu Duan +4
Vision-language models (VLMs) enable visual recognition from semantic class descriptions, which makes them attractive when target annotations are scarce or unavailable. Most deploy…
cs.CV2025
TerraGen: A Unified Multi-Task Layout Generation Framework for Remote Sensing Data Augmentation
Datao Tang, Hao Wang, Yudeng Xin +5
Remote sensing vision tasks require extensive labeled data across multiple, interconnected domains. However, current generative data augmentation frameworks are task-isolated, i.e.…