2022/04/07 by Jiahao Li, Greg Shakhnarovich, Li, Jiahao +3
Computer Science · #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Topic Modeling
paper · pdf · doi:10.48550/arxiv.2204.03647
openalex publication_date 2022/04/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Supervised or weakly supervised methods for phrase localization (textual grounding) either rely on human annotations or some other supervised models, e.g., object detectors. Obtaining these annotations is labor-intensive and may be difficult to scale in practice. We propose to leverage recent advances in contrastive language-vision models, CLIP, pre-trained on image and caption pairs collected from the internet. In its original form, CLIP only outputs an image-level embedding without any spatial resolution. We adapt CLIP to generate high-resolution spatial feature maps. Importantly, we can extract feature maps from both ViT and ResNet CLIP model while maintaining the semantic properties of an image embedding. This provides a natural framework for phrase localization. Our method for phrase localization requires no human annotations or additional training. Extensive experiments show that our method outperforms existing no-training methods in zero-shot phrase localization, and in some cases, it even outperforms supervised methods. Code is available at https://github.com/pals-ttic/adapting-CLIP .