{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/sitta-a-semantic-image-text-alignment-for","title":"Linear Alignment of Vision-language Models for Image Captioning","arxiv_id":"2307.05591","date":"2023-07-10","proceeding":null,"authors":["Fabian Paischer","Markus Hofmarcher","Sepp Hochreiter","Thomas Adler"],"abstract":"Recently, vision-language models like CLIP have advanced the state of the art in a variety of multi-modal tasks including image captioning and caption evaluation. Many approaches adapt CLIP-style models to a downstream task by training a mapping network between CLIP and a language model. This is costly as it usually involves calculating gradients for large models. We propose a more efficient training protocol that fits a linear mapping between image and text embeddings of CLIP via a closed-form solution. This bypasses the need for gradient computation and results in a lightweight captioning method called ReCap, which can be trained up to 1000 times faster than existing lightweight methods. Moreover, we propose two new learning-based image-captioning metrics that build on CLIP score along with our linear mapping. Furthermore, we combine ReCap with our new metrics to design an iterative datastore-augmentation loop (DAL) based on synthetic captions. We evaluate ReCap on MS-COCO, Flickr30k, VizWiz, and MSRVTT. ReCap achieves performance comparable to state-of-the-art lightweight methods on established metrics while outperforming them on our new metrics, which are better aligned with human ratings on Flickr8k-Expert and Flickr8k-Crowdflower. Finally, we demonstrate that ReCap transfers well to other domains and that our DAL leads to a performance boost.","url_abs":"https://arxiv.org/abs/2307.05591v3","url_pdf":"https://arxiv.org/pdf/2307.05591v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"sitta-a-semantic-image-text-alignment-for","repo_url":"https://github.com/ml-jku/semantic-image-text-alignment","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}