Papers › Unleashing the Potential of Consistency Learning for Detecting and Grounding...

Unleashing the Potential of Consistency Learning for Detecting and Grounding Multi-Modal Media Manipulation

6 Jun 2025CVPR 2025 1arXiv:2506.05890archive 2025-07-28

Yiheng Li, Yang Yang, Zichang Tan, Huan Liu, Weihua Chen, Xu Zhou, Zhen Lei

To tackle the threat of fake news, the task of detecting and grounding multi-modal media manipulation DGM4 has received increasing attention. However, most state-of-the-art methods fail to explore the fine-grained consistency within local content, usually resulting in an inadequate perception of detailed forgery and unreliable results. In this paper, we propose a novel approach named Contextual-Semantic Consistency Learning (CSCL) to enhance the fine-grained perception ability of forgery for DGM4. Two branches for image and text modalities are established, each of which contains two cascaded decoders, i.e., Contextual Consistency Decoder (CCD) and Semantic Consistency Decoder (SCD), to capture within-modality contextual consistency and across-modality semantic consistency, respectively. Both CCD and SCD adhere to the same criteria for capturing fine-grained forgery details. To be specific, each module first constructs consistency features by leveraging additional supervision from the heterogeneous information of each token pair. Then, the forgery-aware reasoning or aggregating is adopted to deeply seek forgery cues based on the consistency features. Extensive experiments on DGM4 datasets prove that CSCL achieves new state-of-the-art performance, especially for the results of grounding manipulated content. Codes and weights are avaliable at https://github.com/liyih/CSCL.

PaperPDFConference PDFCodeCode 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 24 code samples harvested from 1 repository linked to this paper: 20 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 1 violated, 9 with no contract checked; 8 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 24 samples from 1 repository, 20 ran (12 with no instrument failure; 8 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.

liyih/cscl officialmentioned in papermentioned on GitHubpytorchMITSyntology: 24 samples, 20 ran (8 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

24 samples harvested: 20 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 1 violated, 9 with no contract checked; 8 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
1ran · violated contract
5ran · our draft was wrong
3ran; the contract check could not run
9ran
4unverified

Licence: 7 of the 24 samples are pointer only, meaning Syntology does not serve that copy's text. For 7 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 liyih/cscl. “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.

liyih/cscl official repository 24 samples, 20 ran (8 instrument-failed) · 4 unverified
adapt_position_encoding in 5 papers code/MultiModal-DeepFake-main/models/METER/clip_model.py ran MIT (permissive) here; the stored copy is pointer only · 24bfe03a8fb0e475 · report fixture: signature model:dict/0/?, patch_size:int/0/int, after:int/0/int, suffix:str/0/str · returned dict · level recorded 2026-09-24
add_multiline_text code/MultiModal-DeepFake-main/utils.py ran MIT (permissive) · 342d33b0c5ebee8f · report fixture: signature image:ndarray/3/int, text:str/0/str, position:tuple/1/int, font:int/0/int, font_scale:float/0/float, font_color:tuple/1/int, thickness:int/0/int, max_width:int/0/int · returned ndarray · level recorded 2026-09-25
all_gather in 119 papers code/MultiModal-DeepFake-main/models/METER/dist_utils.py ran · our draft was wrong MIT (permissive) · 839a33f049497ac2 · report fixture: signature data:dict/0/?, group:NoneType/0/? · returned list · level recorded 2026-09-24
autocontrast_func in 17 papers code/MultiModal-DeepFake-main/dataset/randaugment.py ran; the contract check could not run (RAISES) MIT (permissive) · 78ca1debd9c4ed87 · report fixture: signature img:ndarray/3/int, cutoff:int/0/int · returned ndarray · level recorded 2026-09-22
box_cxcywh_to_xyxy in 60 papers code/MultiModal-DeepFake-main/models/box_ops.py ran · honoured contract fingerprinted MIT (permissive) · e0a06ded5d4f6c3c · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
box_iou in 34 papers code/MultiModal-DeepFake-main/models/box_ops.py ran fingerprinted MIT (permissive) here; the stored copy is pointer only · 7f5165b3c0380ff2 · report fixture: signature boxes1:Tensor/2/float, boxes2:Tensor/2/float, test:bool/0/bool · returned tuple · level recorded 2026-09-24
box_xyxy_to_cxcywh in 37 papers code/MultiModal-DeepFake-main/models/box_ops.py ran · honoured contract fingerprinted MIT (permissive) · 031b02fb990284ba · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
calculate_patch_labels code/MultiModal-DeepFake-main/models/consist_modeling.py ran MIT (permissive) · 22c7fff0fb7d9049 · report fixture: signature images:Tensor/4/float, boxes:Tensor/2/float, fake_text_pos:Tensor/2/float, num_patches:tuple/1/int · returned tuple · level recorded 2026-09-25
compute_acc in 61 papers
census: 3 implementations from 5 papers, 3 distinct outputs across 3 buckets, one shared input per bucket
code/MultiModal-DeepFake-main/utils.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · aa81d03f07735ab8 · report fixture: signature logits:Tensor/2/float, label:Tensor/1/int, reduction:str/0/str · returned float · level recorded 2026-09-22
compute_n_params in 30 papers code/MultiModal-DeepFake-main/utils.py ran · our draft was wrong MIT (permissive) · ad12a494674d23fb · report fixture: signature model:callable/0/?, return_str:bool/0/bool · returned str · level recorded 2026-09-22
coords_2d code/MultiModal-DeepFake-main/models/CSCL.py ran MIT (permissive) · e67c2a64bd9a69e2 · report fixture: signature x_size:int/0/int, y_size:int/0/int · returned Tensor · level recorded 2026-09-25
equalize_func in 17 papers code/MultiModal-DeepFake-main/dataset/randaugment.py ran; the contract check could not run (RAISES) MIT (permissive) · 4c53169f63a1fcef · report fixture: signature img:ndarray/3/int · returned ndarray · level recorded 2026-09-22
gather in 75 papers code/MultiModal-DeepFake-main/models/METER/dist_utils.py ran · our draft was wrong MIT (permissive) · cc8ab2b168b5373d · report fixture: signature data:dict/0/?, dst:int/0/int, group:NoneType/0/? · returned list · level recorded 2026-09-24
get_sscore_label code/MultiModal-DeepFake-main/models/consist_modeling.py ran MIT (permissive) · c04888604cde46ea · report fixture: signature img:Tensor/4/float, fake_img_box:Tensor/2/float, fake_text_pos:Tensor/2/float, len_edge:int/0/int · returned tuple · level recorded 2026-09-25
identity_func in 19 papers code/MultiModal-DeepFake-main/dataset/randaugment.py ran · violated contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 1dd2ab205689d45b · report fixture: signature img:Tensor/4/float · returned Tensor · level recorded 2026-09-22
pos2posemb2d in 5 papers code/MultiModal-DeepFake-main/models/CSCL.py ran fingerprinted MIT (permissive) · fea8a4547c819eec · report fixture: signature pos:Tensor/2/float, num_pos_feats:int/0/int, temperature:int/0/int · returned Tensor · level recorded 2026-09-25
pre_caption in 17 papers code/MultiModal-DeepFake-main/dataset/utils.py ran · our draft was wrong fingerprinted MIT (permissive) · 8a57c3e7d1cf36c7 · report fixture: signature caption:str/0/str, max_words:int/0/int · returned str · level recorded 2026-09-25
pre_question code/MultiModal-DeepFake-main/dataset/utils.py ran fingerprinted MIT (permissive) here; the stored copy is pointer only · 01849cd80343b88a · report fixture: signature question:str/0/str, max_ques_words:int/0/int · returned str · level recorded 2026-09-24
reduce_dict in 73 papers code/MultiModal-DeepFake-main/models/METER/dist_utils.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 53838c15d969eb79 · report fixture: signature input_dict:dict/0/?, average:bool/0/bool · returned dict · level recorded 2026-09-24
score2posemb1d code/MultiModal-DeepFake-main/models/CSCL.py ran fingerprinted MIT (permissive) · 9f85ec8b64bbcaac · report fixture: signature pos:Tensor/2/float, num_pos_feats:int/0/int, temperature:int/0/int · returned Tensor · level recorded 2026-09-25
build_model in 469 papers code/MultiModal-DeepFake-main/models/METER/clip_model.py unverified MIT (permissive) · 84631e1ece975f6b · report
get_sscore_label_text code/MultiModal-DeepFake-main/models/consist_modeling.py unverified MIT (permissive) · a5464e89a64cec02 · report
load_tf_weights_in_bert in 135 papers code/MultiModal-DeepFake-main/models/METER/bert_model.py unverified MIT (permissive) here; the stored copy is pointer only · efbb0f3903b5f779 · report
vqa_eval code/MultiModal-DeepFake-main/dataset/utils.py unverified MIT (permissive) here; the stored copy is pointer only · 53e282c1c632bfa7 · report

Tasks

Decoder

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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