Long-clip: Unlocking The Long-text Capability Of CLIP
2024 · Beichen Zhang, Pan Zhang, Xiaoyi Dong, et al.
Abstract
Contrastive Language-Image Pre-training (CLIP) has been the cornerstone for zero-shot classification, text-image retrieval, and text-image generation by aligning image and text modalities. Despite its widespread adoption, a significant limitation of CLIP lies in the inadequate length of text input. The length of the text token is restricted to 77, and an empirical study shows the actual effective length is even less than 20. This prevents CLIP from handling detailed descriptions, limiting its applications for image retrieval and text-to-image generation with extensive prerequisites. To this end, we propose Long-CLIP as a plug-and-play alternative to CLIP that supports long-text input, retains or even surpasses its zero-shot generalizability, and aligns the CLIP latent space, making it readily replace CLIP without any further adaptation in downstream frameworks. Nevertheless, achieving this goal is far from straightforward, as simplistic fine-tuning can result in a significant degradati
Authors
(none)
Tags
Stats
Related papers
- Finelip: Extending Clip's Reach Via Fine-grained Alignment With Longer Text Inputs (2025)6.34
- Videoclip-xl: Advancing Long Description Understanding For Video CLIP Models (2024)8.35
- CLIP Is Shortsighted: Paying Attention Beyond The First Sentence (2026)0.00
- TULIP: Token-length Upgraded CLIP (2024)3.04
- FG-CLIP: Fine-grained Visual And Textual Alignment (2025)5.75
- Superclip: CLIP With Simple Classification Supervision (2025)0.00
- Mobileclip: Fast Image-text Models Through Multi-modal Reinforced Training (2023)18.12
- Lotlip: Improving Language-image Pre-training For Long Text Understanding (2024)2.26