no code implementations • 17 Apr 2024 • Zhangchi Feng, Richong Zhang, Zhijie Nie
The Composed Image Retrieval (CIR) task aims to retrieve target images using a composed query consisting of a reference image and a modified text.
1 code implementation • 8 Mar 2024 • Hailang Huang, Zhijie Nie, Ziqiao Wang, Ziyu Shang
Furthermore, our method can also boost the uni-modal retrieval performance of image-text retrieval models, enabling it to achieve universal retrieval.
no code implementations • 28 Feb 2024 • Mingxin Li, Richong Zhang, Zhijie Nie
To address these questions, we start from the perspective of gradients and discover that four effective contrastive losses can be integrated into a unified paradigm, which depends on three components: the Gradient Dissipation, the Weight, and the Ratio.
1 code implementation • 12 Sep 2023 • Mingxin Li, Richong Zhang, Zhijie Nie, Yongyi Mao
An intriguing phenomenon in CSE is the significant performance gap between supervised and unsupervised methods, with their only difference lying in the training data.
1 code implementation • 9 Sep 2023 • Zhijie Nie, Richong Zhang, Zhongyuan Wang, Xudong Liu
Current methods for Knowledge-Based Question Answering (KBQA) usually rely on complex training techniques and model frameworks, leading to many limitations in practical applications.