Tripletclip: Improving Compositional Reasoning Of CLIP Via Synthetic Vision-language Negatives

Abstract

Contrastive Language-Image Pretraining (CLIP) models maximize the mutual information between text and visual modalities to learn representations. This makes the nature of the training data a significant factor in the efficacy of CLIP for downstream tasks. However, the lack of compositional diversity in contemporary image-text datasets limits the compositional reasoning ability of CLIP. We show that generating ``hard'' negative captions via in-context learning and synthesizing corresponding negative images with text-to-image generators offers a solution. We introduce a novel contrastive pre-training strategy that leverages these hard negative captions and images in an alternating fashion to train CLIP. We demonstrate that our method, named TripletCLIP, when applied to existing datasets such as CC3M and CC12M, enhances the compositional capabilities of CLIP, resulting in an absolute improvement of over 9% on the SugarCrepe benchmark on an equal computational budget, as well as improvemen

Stats

• citations3
• S2 citations—
• github stars0
• HF likes0
• heat score4.52
• arxiv keypatel2024tripletclip

Related papers

• Semantic Compositions Enhance Vision-language Contrastive Learning (2024)0.00
• Contrasting Intra-modal And Ranking Cross-modal Hard Negatives To Enhance Visio-linguistic Compositional Understanding (2023)12.11
• Advancing Compositional Awareness In CLIP With Efficient Fine-tuning (2025)0.00
• CLIPS: An Enhanced CLIP Framework For Learning With Synthetic Captions (2024)0.00
• Modeling Caption Diversity In Contrastive Vision-language Pretraining (2024)0.00
• Contrastive Vision-language Learning With Paraphrasing And Negation (2025)0.00
• FG-CLIP: Fine-grained Visual And Textual Alignment (2025)5.75
• No Captions, No Problem: Captionless 3D-CLIP Alignment With Hard Negatives Via CLIP Knowledge And Llms (2024)0.00