{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/unleashing-text-to-image-diffusion-models-for-1","title":"Unleashing Text-to-Image Diffusion Models for Visual Perception","arxiv_id":"2303.02153","date":"2023-03-03","proceeding":"ICCV 2023 1","authors":["Wenliang Zhao","Yongming Rao","Zuyan Liu","Benlin Liu","Jie zhou","Jiwen Lu"],"abstract":"Diffusion models (DMs) have become the new trend of generative models and have demonstrated a powerful ability of conditional synthesis. Among those, text-to-image diffusion models pre-trained on large-scale image-text pairs are highly controllable by customizable prompts. Unlike the unconditional generative models that focus on low-level attributes and details, text-to-image diffusion models contain more high-level knowledge thanks to the vision-language pre-training. In this paper, we propose VPD (Visual Perception with a pre-trained Diffusion model), a new framework that exploits the semantic information of a pre-trained text-to-image diffusion model in visual perception tasks. Instead of using the pre-trained denoising autoencoder in a diffusion-based pipeline, we simply use it as a backbone and aim to study how to take full advantage of the learned knowledge. Specifically, we prompt the denoising decoder with proper textual inputs and refine the text features with an adapter, leading to a better alignment to the pre-trained stage and making the visual contents interact with the text prompts. We also propose to utilize the cross-attention maps between the visual features and the text features to provide explicit guidance. Compared with other pre-training methods, we show that vision-language pre-trained diffusion models can be faster adapted to downstream visual perception tasks using the proposed VPD. Extensive experiments on semantic segmentation, referring image segmentation and depth estimation demonstrates the effectiveness of our method. Notably, VPD attains 0.254 RMSE on NYUv2 depth estimation and 73.3% oIoU on RefCOCO-val referring image segmentation, establishing new records on these two benchmarks. Code is available at https://github.com/wl-zhao/VPD","url_abs":"https://arxiv.org/abs/2303.02153v1","url_pdf":"https://arxiv.org/pdf/2303.02153v1.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":"unleashing-text-to-image-diffusion-models-for-1","repo_url":"https://github.com/wl-zhao/VPD","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"unleashing-text-to-image-diffusion-models-for-1","repo_url":"https://github.com/open-mmlab/mmsegmentation/tree/main/configs/vpd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"monocular-depth-estimation","task_name":"Monocular Depth Estimation"},{"task_slug":"referring-expression-segmentation","task_name":"Referring Expression Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"denoising-autoencoder","method_name":"Denoising Autoencoder"},{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/monocular-depth-estimation-on-nyu-depth-v2","task":"Monocular Depth Estimation","dataset":"NYU-Depth V2","model":"VPD","rank_in_archive_order":21,"of":85,"metrics":{"Delta < 1.25":"0.964","Delta < 1.25^2":"0.995","Delta < 1.25^3":"0.999","RMSE":"0.254","absolute relative error":"0.069","log 10":"0.030"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco","task":"Referring Expression Segmentation","dataset":"RefCoCo val","model":"VPD","rank_in_archive_order":21,"of":37,"metrics":{"Overall IoU":"73.25"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2303.02153","atlas_url":"https://app.syntology.ai/?focus=2303.02153","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.02153"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2303.02153"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2303.02153"},"call":"get_harvested_code_for_paper(arxiv_id=\"2303.02153\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2303.02153"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2303.02153\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2303.02153"},"call":"get_concepts_for_paper(arxiv_id=\"2303.02153\")"}],"by_repo":[{"repo":"wl-zhao/VPD","kind":"official","samples":5,"ran":5,"instrument":1,"unverified":0},{"repo":"open-mmlab/mmsegmentation","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2310.05590"],"harvested_for_calls":[{"arxiv_id":"2310.05590","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2310.05590"},"call":"get_harvested_code_for_paper(arxiv_id=\"2310.05590\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2303.02153.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2303.02153.svg"},"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/open-mmlab/mmsegmentation/tree/main/configs/vpd","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/wl-zhao/VPD","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"ran_violates":2,"ran":1,"ran_draft_wrong":1},"n_samples":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":5,"ran":5,"n_ran_checked":4,"n_instrument":1,"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":3,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":3,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":4,"n_ran_without_level_date":1,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","last":"2026-09-25","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","census_is":"Syntology's function-name census ran implementations with this entry name on one shared input per bucket (the positional rank, kind and dtype of each array argument) and counted the distinct output digests (sha256 of the output rounded to 6 decimals). implementations and papers count the compared samples; distinct_outputs counts digests across all buckets; n_buckets is how many shared inputs were used. It is not a statement that any two samples compute one thing, and the name is a string, not an identity.","samples":[{"code_sha256":"b700fb0a3496b255","code_sha256_prefix":"b700fb0a3496b255","entry":"cosine_scheduler","repo":"wl-zhao/VPD","repo_kind":"official","path":"depth/utils.py","file_url":"https://github.com/wl-zhao/VPD/blob/HEAD/depth/utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"base_value:float/0/float, final_value:float/0/float, epochs:int/0/int, niter_per_ep:int/0/int, warmup_epochs:int/0/int, start_warmup_value:float/0/float, warmup_steps:int/0/int","fixture_out_type":"ndarray","level_recorded_at":"2026-09-25T15:11:32.249708+00:00","code_page":"/code/cosine-scheduler","census":null,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from boyazeng/understand_bias, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"b700fb0a3496b255"}},{"code_sha256":"424012cb37b31172","code_sha256_prefix":"424012cb37b31172","entry":"default","repo":"wl-zhao/VPD","repo_kind":"official","path":"vpd/models.py","file_url":"https://github.com/wl-zhao/VPD/blob/HEAD/vpd/models.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"signature":"val:NoneType/0/?, d:callable/0/?","fixture_out_type":"int","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/default","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"424012cb37b31172"}},{"code_sha256":"aa5486a3650902d8","code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":"wl-zhao/VPD","repo_kind":"official","path":"vpd/models.py","file_url":"https://github.com/wl-zhao/VPD/blob/HEAD/vpd/models.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"val:Tensor/1/int","fixture_out_type":"bool","code_page":"/code/exists","census":{"url":"/census/exists","implementations":5,"papers":103,"distinct_outputs":1,"n_buckets":1,"bucket_key":[[1,"int","int64"]],"bucket_index":1,"bucket_label":"arg 1: rank 1, kind int, dtype int64"},"census_bucket_fragment":"bucket-1","licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from ThomasMrY/VCT, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256":"6907f72868217c02","code_sha256_prefix":"6907f72868217c02","entry":"get_num_layer_for_swin","repo":"wl-zhao/VPD","repo_kind":"official","path":"depth/models_depth/optimizer.py","file_url":"https://github.com/wl-zhao/VPD/blob/HEAD/depth/models_depth/optimizer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"var_name:str/0/str, num_max_layer:int/0/int, layers_per_stage:list/1/int","fixture_out_type":"int","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"6907f72868217c02"}},{"code_sha256":"9a299fe5ae09e407","code_sha256_prefix":"9a299fe5ae09e407","entry":"uniq","repo":"wl-zhao/VPD","repo_kind":"official","path":"vpd/models.py","file_url":"https://github.com/wl-zhao/VPD/blob/HEAD/vpd/models.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"arr:list/1/int","fixture_out_type":"dict_keys","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/uniq","census":null,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from JingWu321/MUNBa, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"9a299fe5ae09e407"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"b5bb839558ec192d3aadbeb23233fafd23b357050658ba9633f045b6eff7b13c","record_changed_at":"2026-10-04","record_changed_at_basis":"changed"}