Showing 2024Show all
3 papers · 1 filter
cs.CV2024
Continual Learning for Segment Anything Model Adaptation
Jinglong Yang, Yichen Wu, Jun Cen +3
Although the current different types of SAM adaptation methods have achieved promising performance for various downstream tasks, such as prompt-based ones and adapter-based ones, m…
cs.CV2024
Consistent Prompting for Rehearsal-Free Continual Learning
Zhanxin Gao, Jun Cen, Xiaobin Chang
Continual learning empowers models to adapt autonomously to the ever-changing environment or data streams without forgetting old knowledge. Prompt-based approaches are built on fro…
cs.CV2024
Towards Few-shot Out-of-Distribution Detection
Jiuqing Dong, Yongbin Gao, Heng Zhou +4
Out-of-distribution (OOD) detection is critical for ensuring the reliability of open-world intelligent systems. Despite the notable advancements in existing OOD detection methodolo…