4 papers
Raw Data Matters: Enhancing Prompt Tuning by Internal Augmentation on Vision-Language Models
Haoyang Li, Liang Wang, Chao Wang +4
For CLIP-based prompt tuning, introducing more data as additional knowledge for enhancing fine-tuning process is proved to be an effective approach. Existing data amplification str…
VIKSER: Visual Knowledge-Driven Self-Reinforcing Reasoning Framework
Chao Wang, Chunbai Zhang, Yongxiao Tian +2
Visual reasoning refers to the task of solving questions about visual information. Current visual reasoning methods typically employ pre-trained vision-language model (VLM) strateg…
DPC: Dual-Prompt Collaboration for Tuning Vision-Language Models
Haoyang Li, Liang Wang, Chao Wang +3
The Base-New Trade-off (BNT) problem universally exists during the optimization of CLIP-based prompt tuning, where continuous fine-tuning on base (target) classes leads to a simult…
PhiP-G: Physics-Guided Text-to-3D Compositional Scene Generation
Qixuan Li, Chao Wang, Zongjin He +1
Text-to-3D asset generation has achieved significant optimization under the supervision of 2D diffusion priors. However, when dealing with compositional scenes, existing methods en…