{"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/191013321","title":"Semantic Object Accuracy for Generative Text-to-Image Synthesis","arxiv_id":"1910.13321","date":"2019-10-29","proceeding":null,"authors":["Tobias Hinz","Stefan Heinrich","Stefan Wermter"],"abstract":"Generative adversarial networks conditioned on textual image descriptions are capable of generating realistic-looking images. However, current methods still struggle to generate images based on complex image captions from a heterogeneous domain. Furthermore, quantitatively evaluating these text-to-image models is challenging, as most evaluation metrics only judge image quality but not the conformity between the image and its caption. To address these challenges we introduce a new model that explicitly models individual objects within an image and a new evaluation metric called Semantic Object Accuracy (SOA) that specifically evaluates images given an image caption. The SOA uses a pre-trained object detector to evaluate if a generated image contains objects that are mentioned in the image caption, e.g. whether an image generated from \"a car driving down the street\" contains a car. We perform a user study comparing several text-to-image models and show that our SOA metric ranks the models the same way as humans, whereas other metrics such as the Inception Score do not. Our evaluation also shows that models which explicitly model objects outperform models which only model global image characteristics.","url_abs":"https://arxiv.org/abs/1910.13321v2","url_pdf":"https://arxiv.org/pdf/1910.13321v2.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":"191013321","repo_url":"https://github.com/tohinz/semantic-object-accuracy-for-generative-text-to-image-synthesis","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"191013321","repo_url":"https://github.com/tohinz/multiple-objects-gan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"},{"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":"OP-GAN","rank_in_archive_order":50,"of":69,"metrics":{"FID":"24.70","Inception score":"27.88","SOA-C":"35.85"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1910.13321","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.13321"}},"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/tohinz/multiple-objects-gan","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tohinz/semantic-object-accuracy-for-generative-text-to-image-synthesis","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":4,"unverified":19},"by_repo_kind":{"official":{"samples":13,"ran":0,"repositories":1},"listed":{"samples":10,"ran":4,"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":"19379807ba70daaa","entry":"conv1x1","repo":"tohinz/multiple-objects-gan","repo_kind":"listed","path":"code/coco/attngan/model.py","file_url":"https://github.com/tohinz/multiple-objects-gan/blob/HEAD/code/coco/attngan/model.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"19379807ba70daaa"}},{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":"tohinz/multiple-objects-gan","repo_kind":"listed","path":"code/clevr/model.py","file_url":"https://github.com/tohinz/multiple-objects-gan/blob/HEAD/code/clevr/model.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"e0c14774d8283a63","entry":"cosine_similarity","repo":"tohinz/multiple-objects-gan","repo_kind":"listed","path":"code/coco/attngan/losses.py","file_url":"https://github.com/tohinz/multiple-objects-gan/blob/HEAD/code/coco/attngan/losses.py","link_basis":"plan_row","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":"e0c14774d8283a63"}},{"code_sha256_prefix":"721bc7234edf9845","entry":"upBlock","repo":"tohinz/multiple-objects-gan","repo_kind":"listed","path":"code/clevr/model.py","file_url":"https://github.com/tohinz/multiple-objects-gan/blob/HEAD/code/clevr/model.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"721bc7234edf9845"}},{"code_sha256_prefix":"f5534bc5c6aff8c5","entry":"calc_iou","repo":"tohinz/semantic-object-accuracy-for-generative-text-to-image-synthesis","repo_kind":"official","path":"SOA/calculate_soa.py","file_url":"https://github.com/tohinz/semantic-object-accuracy-for-generative-text-to-image-synthesis/blob/HEAD/SOA/calculate_soa.py","link_basis":"first_harvest_node","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":"f5534bc5c6aff8c5"}},{"code_sha256_prefix":"b4ebb326c7ea58dd","entry":"calc_overall_class_average_accuracy","repo":"tohinz/semantic-object-accuracy-for-generative-text-to-image-synthesis","repo_kind":"official","path":"SOA/calculate_soa.py","file_url":"https://github.com/tohinz/semantic-object-accuracy-for-generative-text-to-image-synthesis/blob/HEAD/SOA/calculate_soa.py","link_basis":"first_harvest_node","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":"b4ebb326c7ea58dd"}},{"code_sha256_prefix":"e7d41b0d52cc6652","entry":"calc_recall","repo":"tohinz/semantic-object-accuracy-for-generative-text-to-image-synthesis","repo_kind":"official","path":"SOA/calculate_soa.py","file_url":"https://github.com/tohinz/semantic-object-accuracy-for-generative-text-to-image-synthesis/blob/HEAD/SOA/calculate_soa.py","link_basis":"first_harvest_node","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":"e7d41b0d52cc6652"}},{"code_sha256_prefix":"8435d7d3950b360b","entry":"compute_transformation_matrix","repo":"tohinz/multiple-objects-gan","repo_kind":"listed","path":"code/clevr/miscc/utils.py","file_url":"https://github.com/tohinz/multiple-objects-gan/blob/HEAD/code/clevr/miscc/utils.py","link_basis":"first_harvest_node","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":"8435d7d3950b360b"}},{"code_sha256_prefix":"272d0358125c681c","entry":"compute_transformation_matrix_inverse","repo":"tohinz/multiple-objects-gan","repo_kind":"listed","path":"code/clevr/miscc/utils.py","file_url":"https://github.com/tohinz/multiple-objects-gan/blob/HEAD/code/clevr/miscc/utils.py","link_basis":"first_harvest_node","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":"272d0358125c681c"}},{"code_sha256_prefix":"1e9b9a9b96ddfe5f","entry":"conv1x1","repo":"tohinz/semantic-object-accuracy-for-generative-text-to-image-synthesis","repo_kind":"official","path":"OP-GAN/code/GlobalAttention.py","file_url":"https://github.com/tohinz/semantic-object-accuracy-for-generative-text-to-image-synthesis/blob/HEAD/OP-GAN/code/GlobalAttention.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":"1e9b9a9b96ddfe5f"}},{"code_sha256_prefix":"3fe3a379cddb6a43","entry":"crop_imgs","repo":"tohinz/multiple-objects-gan","repo_kind":"listed","path":"code/coco/attngan/datasets.py","file_url":"https://github.com/tohinz/multiple-objects-gan/blob/HEAD/code/coco/attngan/datasets.py","link_basis":"first_harvest_node","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":"3fe3a379cddb6a43"}},{"code_sha256_prefix":"703847df44b817c2","entry":"crop_imgs","repo":"tohinz/semantic-object-accuracy-for-generative-text-to-image-synthesis","repo_kind":"official","path":"OP-GAN/code/datasets.py","file_url":"https://github.com/tohinz/semantic-object-accuracy-for-generative-text-to-image-synthesis/blob/HEAD/OP-GAN/code/datasets.py","link_basis":"first_harvest_node","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":"703847df44b817c2"}},{"code_sha256_prefix":"9da68638a70fdd3f","entry":"drawCaption","repo":"tohinz/semantic-object-accuracy-for-generative-text-to-image-synthesis","repo_kind":"official","path":"OP-GAN/code/miscc/utils.py","file_url":"https://github.com/tohinz/semantic-object-accuracy-for-generative-text-to-image-synthesis/blob/HEAD/OP-GAN/code/miscc/utils.py","link_basis":"first_harvest_node","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":"9da68638a70fdd3f"}},{"code_sha256_prefix":"6990deae791a4ec6","entry":"func_attention","repo":"tohinz/multiple-objects-gan","repo_kind":"listed","path":"code/coco/attngan/GlobalAttention.py","file_url":"https://github.com/tohinz/multiple-objects-gan/blob/HEAD/code/coco/attngan/GlobalAttention.py","link_basis":"first_harvest_node","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":"6990deae791a4ec6"}},{"code_sha256_prefix":"98438c5b9090c833","entry":"get_imgs","repo":"tohinz/semantic-object-accuracy-for-generative-text-to-image-synthesis","repo_kind":"official","path":"OP-GAN/code/datasets.py","file_url":"https://github.com/tohinz/semantic-object-accuracy-for-generative-text-to-image-synthesis/blob/HEAD/OP-GAN/code/datasets.py","link_basis":"first_harvest_node","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":"98438c5b9090c833"}},{"code_sha256_prefix":"2c0804d9b98af380","entry":"get_label","repo":"tohinz/semantic-object-accuracy-for-generative-text-to-image-synthesis","repo_kind":"official","path":"SOA/util.py","file_url":"https://github.com/tohinz/semantic-object-accuracy-for-generative-text-to-image-synthesis/blob/HEAD/SOA/util.py","link_basis":"first_harvest_node","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":"2c0804d9b98af380"}},{"code_sha256_prefix":"c44c472ef9c707e8","entry":"load_classes","repo":"tohinz/semantic-object-accuracy-for-generative-text-to-image-synthesis","repo_kind":"official","path":"SOA/util.py","file_url":"https://github.com/tohinz/semantic-object-accuracy-for-generative-text-to-image-synthesis/blob/HEAD/SOA/util.py","link_basis":"first_harvest_node","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":"c44c472ef9c707e8"}},{"code_sha256_prefix":"ce73ac36a39a4b99","entry":"load_file","repo":"tohinz/semantic-object-accuracy-for-generative-text-to-image-synthesis","repo_kind":"official","path":"SOA/util.py","file_url":"https://github.com/tohinz/semantic-object-accuracy-for-generative-text-to-image-synthesis/blob/HEAD/SOA/util.py","link_basis":"first_harvest_node","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":"ce73ac36a39a4b99"}},{"code_sha256_prefix":"f4106ae0d85d225b","entry":"load_validation_data","repo":"tohinz/multiple-objects-gan","repo_kind":"listed","path":"code/clevr/miscc/utils.py","file_url":"https://github.com/tohinz/multiple-objects-gan/blob/HEAD/code/clevr/miscc/utils.py","link_basis":"first_harvest_node","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":"f4106ae0d85d225b"}},{"code_sha256_prefix":"4587b69d57d6511b","entry":"parse_cfg","repo":"tohinz/semantic-object-accuracy-for-generative-text-to-image-synthesis","repo_kind":"official","path":"SOA/darknet.py","file_url":"https://github.com/tohinz/semantic-object-accuracy-for-generative-text-to-image-synthesis/blob/HEAD/SOA/darknet.py","link_basis":"first_harvest_node","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":"4587b69d57d6511b"}},{"code_sha256_prefix":"98d805e89bf7c844","entry":"prepare_data","repo":"tohinz/semantic-object-accuracy-for-generative-text-to-image-synthesis","repo_kind":"official","path":"OP-GAN/code/datasets.py","file_url":"https://github.com/tohinz/semantic-object-accuracy-for-generative-text-to-image-synthesis/blob/HEAD/OP-GAN/code/datasets.py","link_basis":"first_harvest_node","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":"98d805e89bf7c844"}},{"code_sha256_prefix":"4cb5fe22f24b4c13","entry":"stn","repo":"tohinz/multiple-objects-gan","repo_kind":"listed","path":"code/clevr/model.py","file_url":"https://github.com/tohinz/multiple-objects-gan/blob/HEAD/code/clevr/model.py","link_basis":"first_harvest_node","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":"4cb5fe22f24b4c13"}},{"code_sha256_prefix":"05d7f85ab3f4ff30","entry":"stn","repo":"tohinz/semantic-object-accuracy-for-generative-text-to-image-synthesis","repo_kind":"official","path":"OP-GAN/code/model.py","file_url":"https://github.com/tohinz/semantic-object-accuracy-for-generative-text-to-image-synthesis/blob/HEAD/OP-GAN/code/model.py","link_basis":"first_harvest_node","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":"05d7f85ab3f4ff30"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}