{"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/unifying-multimodal-transformer-for-bi","title":"Unifying Multimodal Transformer for Bi-directional Image and Text Generation","arxiv_id":"2110.09753","date":"2021-10-19","proceeding":null,"authors":["Yupan Huang","Hongwei Xue","Bei Liu","Yutong Lu"],"abstract":"We study the joint learning of image-to-text and text-to-image generations, which are naturally bi-directional tasks. Typical existing works design two separate task-specific models for each task, which impose expensive design efforts. In this work, we propose a unified image-and-text generative framework based on a single multimodal model to jointly study the bi-directional tasks. We adopt Transformer as our unified architecture for its strong performance and task-agnostic design. Specifically, we formulate both tasks as sequence generation tasks, where we represent images and text as unified sequences of tokens, and the Transformer learns multimodal interactions to generate sequences. We further propose two-level granularity feature representations and sequence-level training to improve the Transformer-based unified framework. Experiments show that our approach significantly improves previous Transformer-based model X-LXMERT's FID from 37.0 to 29.9 (lower is better) for text-to-image generation, and improves CIDEr-D score from 100.9% to 122.6% for fine-tuned image-to-text generation on the MS-COCO dataset. Our code is available online.","url_abs":"https://arxiv.org/abs/2110.09753v1","url_pdf":"https://arxiv.org/pdf/2110.09753v1.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":"unifying-multimodal-transformer-for-bi","repo_url":"https://github.com/researchmm/generate-it","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"image-to-text","task_name":"Image to text"},{"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"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2110.09753","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.09753"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/researchmm/generate-it","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":8},"by_repo_kind":{"official":{"samples":8,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"6a609c6155c138b3","entry":"array_to_str","repo":"researchmm/generate-it","repo_kind":"official","path":"it-generator/loss.py","file_url":"https://github.com/researchmm/generate-it/blob/HEAD/it-generator/loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6a609c6155c138b3"}},{"code_sha256_prefix":"54027d44ffd92b3d","entry":"clean_text","repo":"researchmm/generate-it","repo_kind":"official","path":"diverse-it-generator/sample_images.py","file_url":"https://github.com/researchmm/generate-it/blob/HEAD/diverse-it-generator/sample_images.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"54027d44ffd92b3d"}},{"code_sha256_prefix":"2b8adb12cabcf6e3","entry":"collate_fn_test","repo":"researchmm/generate-it","repo_kind":"official","path":"diverse-it-generator/dataset.py","file_url":"https://github.com/researchmm/generate-it/blob/HEAD/diverse-it-generator/dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2b8adb12cabcf6e3"}},{"code_sha256_prefix":"8c40495897857bbf","entry":"collate_fn_train","repo":"researchmm/generate-it","repo_kind":"official","path":"diverse-it-generator/dataset.py","file_url":"https://github.com/researchmm/generate-it/blob/HEAD/diverse-it-generator/dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8c40495897857bbf"}},{"code_sha256_prefix":"894007cc85d7765f","entry":"eval_clipscore","repo":"researchmm/generate-it","repo_kind":"official","path":"it-generator/evaluate_images.py","file_url":"https://github.com/researchmm/generate-it/blob/HEAD/it-generator/evaluate_images.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"894007cc85d7765f"}},{"code_sha256_prefix":"97216c8f596bae40","entry":"eval_rprec","repo":"researchmm/generate-it","repo_kind":"official","path":"it-generator/evaluate_images.py","file_url":"https://github.com/researchmm/generate-it/blob/HEAD/it-generator/evaluate_images.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"97216c8f596bae40"}},{"code_sha256_prefix":"8f915c7ceb3fc46f","entry":"eval_rprec_hard","repo":"researchmm/generate-it","repo_kind":"official","path":"it-generator/evaluate_images.py","file_url":"https://github.com/researchmm/generate-it/blob/HEAD/it-generator/evaluate_images.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8f915c7ceb3fc46f"}},{"code_sha256_prefix":"df768a32f36d7728","entry":"to_contiguous","repo":"researchmm/generate-it","repo_kind":"official","path":"it-generator/loss.py","file_url":"https://github.com/researchmm/generate-it/blob/HEAD/it-generator/loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"df768a32f36d7728"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}