3 papers
cs.CV2025
TokenSwap: Backdoor Attack on the Compositional Understanding of Large Vision-Language Models
Zhifang Zhang, Qiqi Tao, Jiaqi Lv +3
Large vision-language models (LVLMs) have achieved impressive performance across a wide range of vision-language tasks, while they remain vulnerable to backdoor attacks. Existing b…
cs.CV2024
Enhancing Generalizability of Representation Learning for Data-Efficient 3D Scene Understanding
Yunsong Wang, Na Zhao, Gim Hee Lee
The field of self-supervised 3D representation learning has emerged as a promising solution to alleviate the challenge presented by the scarcity of extensive, well-annotated datase…
cs.CV2024
Syn-to-Real Unsupervised Domain Adaptation for Indoor 3D Object Detection
Yunsong Wang, Na Zhao, Gim Hee Lee
The use of synthetic data in indoor 3D object detection offers the potential of greatly reducing the manual labor involved in 3D annotations and training effective zero-shot detect…