Papers › Exploring Discrete Diffusion Models for Image Captioning

Exploring Discrete Diffusion Models for Image Captioning

21 Nov 2022arXiv:2211.11694archive 2025-07-28

Zixin Zhu, Yixuan Wei, JianFeng Wang, Zhe Gan, Zheng Zhang, Le Wang, Gang Hua, Lijuan Wang, Zicheng Liu, Han Hu

The image captioning task is typically realized by an auto-regressive method that decodes the text tokens one by one. We present a diffusion-based captioning model, dubbed the name DDCap, to allow more decoding flexibility. Unlike image generation, where the output is continuous and redundant with a fixed length, texts in image captions are categorical and short with varied lengths. Therefore, naively applying the discrete diffusion model to text decoding does not work well, as shown in our experiments. To address the performance gap, we propose several key techniques including best-first inference, concentrated attention mask, text length prediction, and image-free training. On COCO without additional caption pre-training, it achieves a CIDEr score of 117.8, which is +5.0 higher than the auto-regressive baseline with the same architecture in the controlled setting. It also performs +26.8 higher CIDEr score than the auto-regressive baseline (230.3 v.s.203.5) on a caption infilling task. With 4M vision-language pre-training images and the base-sized model, we reach a CIDEr score of 125.1 on COCO, which is competitive to the best well-developed auto-regressive frameworks. The code is available at https://github.com/buxiangzhiren/DDCap.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 18 code samples harvested from 1 repository linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 2 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 18 samples from 1 repository, 14 ran (14 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

buxiangzhiren/ddcap officialmentioned in papermentioned on GitHubpytorchMITSyntology: 18 samples, 14 ran (0 instrument-failed) · 4 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

18 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 2 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
12ran
4unverified

Licence: 5 of the 18 samples are pointer only, meaning Syntology does not serve that copy's text. For 5 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from buxiangzhiren/ddcap. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives 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” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

buxiangzhiren/ddcap official repository 18 samples, 14 ran (0 instrument-failed) · 4 unverified
add_period parse_conceptual.py ran fingerprinted MIT (permissive) · c68cb2401825d6a1 · report fixture: signature caption:str/0/str · returned str · level recorded 2026-09-25
check_imports in 15 papers dynamic_module_utils.py ran MIT (permissive) · 5a97e7f261c6118d · report fixture: signature filename:str/0/str · returned list · level recorded 2026-09-25
find_pruneable_heads_and_indices in 19 papers fix_pre.py ran MIT (permissive) · adea8f61592be69f · report fixture: signature heads:list/1/int, n_heads:int/0/int, head_size:int/0/int, already_pruned_heads:set/0/? · returned tuple · level recorded 2026-09-25
generate2 in 6 papers predict.py ran MIT (permissive) here; the stored copy is pointer only · e33b112514a9e4b0 · report fixture: signature model:callable/0/?, tokenizer:MinimalTokenizer/0/?, tokens:NoneType/0/?, prompt:str/0/str, embed:NoneType/0/?, entry_count:int/0/int, entry_length:int/0/int, top_p:float/0/float, temperature:float/0/float, stop_token:str/0/str · returned str · level recorded 2026-09-24
generate_beam in 5 papers predict.py ran MIT (permissive) here; the stored copy is pointer only · 883320eb62f15d12 · report fixture: signature model:callable/0/?, tokenizer:MinimalTokenizer/0/?, beam_size:int/0/int, prompt:str/0/str, embed:NoneType/0/?, entry_length:int/0/int, temperature:float/0/float, stop_token:str/0/str · returned list · level recorded 2026-09-24
get_image in 52 papers parse_conceptual.py ran MIT (permissive) · 0a286fb23ba005b9 · report fixture: signature url:str/0/str, out_path:str/0/str, timeout:int/0/int · returned bool · level recorded 2026-09-24
get_model_parameters_info misc.py ran MIT (permissive) · 7d86410784062a90 · report fixture: signature model:callable/0/? · returned dict · level recorded 2026-09-25
get_relative_import_files in 28 papers dynamic_module_utils.py ran MIT (permissive) · 373405b421a7ccd1 · report fixture: signature module_file:str/0/str · returned list · level recorded 2026-09-25
get_relative_imports in 28 papers dynamic_module_utils.py ran MIT (permissive) · 9f0143385b707e8a · report fixture: signature module_file:str/0/str · returned list · level recorded 2026-09-25
log_1_min_a in 13 papers train_tclip.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 479771b269fc5883 · report fixture: signature a:Tensor/2/float · returned Tensor · level recorded 2026-09-22
log_add_exp in 12 papers train_tclip.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 032c0dece6594020 · report fixture: signature a:Tensor/2/float, b:Tensor/2/float · returned Tensor · level recorded 2026-09-22
merge_opts_to_config misc.py ran MIT (permissive) · 66531358d7cefe44 · report fixture: signature config:dict/0/?, opts:list/1/str · returned dict · level recorded 2026-09-25
modify_config_for_debug misc.py ran MIT (permissive) · 647f36aefa59b564 · report fixture: signature config:dict/0/? · returned dict · level recorded 2026-09-25
thread in 5 papers parse_conceptual.py ran MIT (permissive) · 50449115c68a0ddb · report fixture: signature urls:list/1/tuple, thread_id:int/0/int, progress:tqdm/0/?, lock:lock/0/?, suffix:str/0/str, conceptual_root:str/0/str · returned int · level recorded 2026-09-24
build_model in 469 papers clip1/model.py unverified MIT (permissive) · 8b17971afcbd7a4f · report
build_scheduler in 56 papers lr_scheduler.py unverified MIT (permissive) · 5e666c43b8dba5d1 · report
load_tf_weights_in_gpt2 in 68 papers tf_adpt.py unverified MIT (permissive) here; the stored copy is pointer only · cb4e99dd4b50f69d · report

Tasks

Image CaptioningImage Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Diffusion

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections