{"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/dm-gan-dynamic-memory-generative-adversarial","title":"DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis","arxiv_id":"1904.01310","date":"2019-04-02","proceeding":"CVPR 2019 6","authors":["Minfeng Zhu","Pingbo Pan","Wei Chen","Yi Yang"],"abstract":"In this paper, we focus on generating realistic images from text\ndescriptions. Current methods first generate an initial image with rough shape\nand color, and then refine the initial image to a high-resolution one. Most\nexisting text-to-image synthesis methods have two main problems. (1) These\nmethods depend heavily on the quality of the initial images. If the initial\nimage is not well initialized, the following processes can hardly refine the\nimage to a satisfactory quality. (2) Each word contributes a different level of\nimportance when depicting different image contents, however, unchanged text\nrepresentation is used in existing image refinement processes. In this paper,\nwe propose the Dynamic Memory Generative Adversarial Network (DM-GAN) to\ngenerate high-quality images. The proposed method introduces a dynamic memory\nmodule to refine fuzzy image contents, when the initial images are not well\ngenerated. A memory writing gate is designed to select the important text\ninformation based on the initial image content, which enables our method to\naccurately generate images from the text description. We also utilize a\nresponse gate to adaptively fuse the information read from the memories and the\nimage features. We evaluate the DM-GAN model on the Caltech-UCSD Birds 200\ndataset and the Microsoft Common Objects in Context dataset. Experimental\nresults demonstrate that our DM-GAN model performs favorably against the\nstate-of-the-art approaches.","url_abs":"http://arxiv.org/abs/1904.01310v1","url_pdf":"http://arxiv.org/pdf/1904.01310v1.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":"dm-gan-dynamic-memory-generative-adversarial","repo_url":"https://github.com/MinfengZhu/DM-GAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"dm-gan-dynamic-memory-generative-adversarial","repo_url":"https://github.com/huiyegit/T2I_CL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"dm-gan-dynamic-memory-generative-adversarial","repo_url":"https://github.com/senmaoy/recurrent-affine-transformation-for-text-to-image-synthesis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"dm-gan-dynamic-memory-generative-adversarial","repo_url":"https://github.com/usydnlp/VICTR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"text-to-image-generation","task_name":"Text-to-Image Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/text-to-image-generation-on-coco","task":"Text-to-Image Generation","dataset":"COCO (Common Objects in Context)","model":"DM-GAN","rank_in_archive_order":60,"of":69,"metrics":{"FID":"32.64","Inception score":"30.49","SOA-C":"33.44"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-image-generation-on-multi-modal","task":"Text-to-Image Generation","dataset":"Multi-Modal-CelebA-HQ","model":"DM-GAN","rank_in_archive_order":9,"of":10,"metrics":{"Acc":"16.4","FID":"131.05","LPIPS":"0.544","Real":"16.9"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.01310","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.01310"}},"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/huiyegit/T2I_CL","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/senmaoy/recurrent-affine-transformation-for-text-to-image-synthesis","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/usydnlp/VICTR","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MinfengZhu/DM-GAN","reach":null}],"summary":{"ran_draft_wrong":3,"ran_fixture":1,"unverified":1},"by_repo_kind":{"listed":{"samples":4,"ran":4,"repositories":2}},"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":1,"samples":[{"code_sha256_prefix":"177298ecedde13ed","entry":"calculate_activation_statistics","repo":"MinfengZhu/DM-GAN","repo_kind":"listed","path":"eval/FID/fid_score.py","file_url":"https://github.com/MinfengZhu/DM-GAN/blob/HEAD/eval/FID/fid_score.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"177298ecedde13ed"}},{"code_sha256_prefix":"25ef415d07e43e6f","entry":"calculate_frechet_distance","repo":"MinfengZhu/DM-GAN","repo_kind":"listed","path":"eval/FID/fid_score.py","file_url":"https://github.com/MinfengZhu/DM-GAN/blob/HEAD/eval/FID/fid_score.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"25ef415d07e43e6f"}},{"code_sha256_prefix":"eb21740d88a30ecb","entry":"get_activations","repo":"MinfengZhu/DM-GAN","repo_kind":"listed","path":"eval/FID/fid_score.py","file_url":"https://github.com/MinfengZhu/DM-GAN/blob/HEAD/eval/FID/fid_score.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eb21740d88a30ecb"}},{"code_sha256_prefix":"be7c4a676b9f1e19","entry":"l2norm","repo":"huiyegit/T2I_CL","repo_kind":"listed","path":"DM-GAN+CL/code/pretrain_DAMSM.py","file_url":"https://github.com/huiyegit/T2I_CL/blob/HEAD/DM-GAN%2BCL/code/pretrain_DAMSM.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"be7c4a676b9f1e19"}},{"code_sha256_prefix":"b85a728ed7aaaade","entry":"preprocess","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"b85a728ed7aaaade"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}