{"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/l-verse-bidirectional-generation-between","title":"L-Verse: Bidirectional Generation Between Image and Text","arxiv_id":"2111.11133","date":"2021-11-22","proceeding":"CVPR 2022 1","authors":["TaeHoon Kim","Gwangmo Song","Sihaeng Lee","Sangyun Kim","Yewon Seo","Soonyoung Lee","Seung Hwan Kim","Honglak Lee","Kyunghoon Bae"],"abstract":"Far beyond learning long-range interactions of natural language, transformers are becoming the de-facto standard for many vision tasks with their power and scalability. Especially with cross-modal tasks between image and text, vector quantized variational autoencoders (VQ-VAEs) are widely used to make a raw RGB image into a sequence of feature vectors. To better leverage the correlation between image and text, we propose L-Verse, a novel architecture consisting of feature-augmented variational autoencoder (AugVAE) and bidirectional auto-regressive transformer (BiART) for image-to-text and text-to-image generation. Our AugVAE shows the state-of-the-art reconstruction performance on ImageNet1K validation set, along with the robustness to unseen images in the wild. Unlike other models, BiART can distinguish between image (or text) as a conditional reference and a generation target. L-Verse can be directly used for image-to-text or text-to-image generation without any finetuning or extra object detection framework. In quantitative and qualitative experiments, L-Verse shows impressive results against previous methods in both image-to-text and text-to-image generation on MS-COCO Captions. We furthermore assess the scalability of L-Verse architecture on Conceptual Captions and present the initial result of bidirectional vision-language representation learning on general domain.","url_abs":"https://arxiv.org/abs/2111.11133v10","url_pdf":"https://arxiv.org/pdf/2111.11133v10.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":"l-verse-bidirectional-generation-between","repo_url":"https://github.com/tgisaturday/L-Verse","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"image-reconstruction","task_name":"Image Reconstruction"},{"task_slug":"image-to-text","task_name":"Image to text"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"text-to-image-generation-1","task_name":"Text to Image Generation"},{"task_slug":"text-to-image-generation","task_name":"Text-to-Image Generation"},{"task_slug":"zero-shot-text-to-image-generation","task_name":"Zero-Shot Text-to-Image Generation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"vq-vae","method_name":"VQ-VAE"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-captioning-on-coco-captions","task":"Image Captioning","dataset":"COCO Captions","model":"L-Verse","rank_in_archive_order":20,"of":41,"metrics":{"BLEU-4":"39.9","METEOR":"31.4","ROUGE-L":"60.4","SPICE":"23.3"},"uses_additional_data":false},{"leaderboard":"/sota/image-reconstruction-on-imagenet-256x256","task":"Image Reconstruction","dataset":"ImageNet 256x256","model":"AugVAE-ML","rank_in_archive_order":1,"of":2,"metrics":{"FID":"1.04"},"uses_additional_data":false},{"leaderboard":"/sota/image-reconstruction-on-imagenet-256x256","task":"Image Reconstruction","dataset":"ImageNet 256x256","model":"AugVAE-SL","rank_in_archive_order":2,"of":2,"metrics":{"FID":"3.28"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-image-generation-on-coco","task":"Text-to-Image Generation","dataset":"COCO (Common Objects in Context)","model":"L-Verse-CC","rank_in_archive_order":63,"of":69,"metrics":{"FID":"37.2","FID-1":"31.6","FID-2":"25.7","FID-4":"21.4","FID-8":"21.1"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-image-generation-on-coco","task":"Text-to-Image Generation","dataset":"COCO (Common Objects in Context)","model":"L-Verse","rank_in_archive_order":64,"of":69,"metrics":{"FID":"45.8","FID-1":"41.9","FID-2":"35.5","FID-4":"30.2","FID-8":"29.83"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2111.11133","atlas_url":"https://app.syntology.ai/?focus=2111.11133","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}