no code implementations • 29 Jan 2024 • Shiyin Dong, Mingrui Zhu, Kun Cheng, Nannan Wang, Xinbo Gao
Our purpose is to establish a unified visual perception framework, capitalizing on the potential synergies between generative and discriminative models.
no code implementations • 24 Nov 2023 • Ruoyu Zhao, Mingrui Zhu, Shiyin Dong, Nannan Wang, Xinbo Gao
We propose CatVersion, an inversion-based method that learns the personalized concept through a handful of examples.
no code implementations • 9 May 2023 • Shiyin Dong, Mingrui Zhu, Nannan Wang, Xinbo Gao
Zero-shot sketch-based image retrieval (ZS-SBIR) is challenging due to the cross-domain nature of sketches and photos, as well as the semantic gap between seen and unseen image distributions.