LLM2CLIP: Extending the Capability Boundaries of CLIP through Large Language Models Weiquan Huang 1 , Aoqi Wu 1 , Yifan Yang 2† , Xufang Luo 2 , Yuqing Yang 2 , Liang Hu 1 , Qi Dai 2 , Xiyang Dai 2 , Dongdong Chen 2 , Chong Luo 2 , Lili Qiu 2 1 Tongji Universiy, 2 Microsoft Corporation Equal contribution † Corresponding to: yifanyang@microsoft.com [📂 GitHub] [🆕 Blog] [📜 LLM2CLIP] In this paper, we propose LLM2CLIP, a novel approach that embraces the power of LLMs to unlock CLIP’s potential. By fine tuning the LLM in the caption space with contrastive learning, we extract its textual capabilities into the output embeddings, significantly improving the output layer’s textual discriminability. We then design an efficient training process where the fine tuned LLM acts as a powerful teacher for CLIP’s visual encoder. Thanks to the LLM’s presence, we can now incorporate longer and more complex captions without being restricted by vanilla CLIP text encoder’s context window and ability limitations. Our experiments demonstrate that this approach brings substantial improvements in cross modal tasks. Our method directly boosted the performance of the previously SOTA EVA02 model by 16.5% on…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy