4 papers
The Solution for the 5th GCAIAC Zero-shot Referring Expression Comprehension Challenge
Longfei Huang, Feng Yu, Zhihao Guan +2
This report presents a solution for the zero-shot referring expression comprehension task. Visual-language multimodal base models (such as CLIP, SAM) have gained significant attent…
The Solution for the sequential task continual learning track of the 2nd Greater Bay Area International Algorithm Competition
Sishun Pan, Xixian Wu, Tingmin Li +4
This paper presents a data-free, parameter-isolation-based continual learning algorithm we developed for the sequential task continual learning track of the 2nd Greater Bay Area In…
The Solution for Language-Enhanced Image New Category Discovery
Haonan Xu, Dian Chao, Xiangyu Wu +2
Treating texts as images, combining prompts with textual labels for prompt tuning, and leveraging the alignment properties of CLIP have been successfully applied in zero-shot multi…
The Solution for the AIGC Inference Performance Optimization Competition
Sishun Pan, Haonan Xu, Zhonghua Wan +1
In recent years, the rapid advancement of large-scale pre-trained language models based on transformer architectures has revolutionized natural language processing tasks. Among the…