Papers › Learning Visually-Grounded Semantics from Contrastive Adversarial Samples

Learning Visually-Grounded Semantics from Contrastive Adversarial Samples

27 Jun 2018COLING 2018 8arXiv:1806.10348archive 2025-07-28

Haoyue Shi, Jiayuan Mao, Tete Xiao, Yuning Jiang, Jian Sun

We study the problem of grounding distributional representations of texts on the visual domain, namely visual-semantic embeddings (VSE for short). Begin with an insightful adversarial attack on VSE embeddings, we show the limitation of current frameworks and image-text datasets (e.g., MS-COCO) both quantitatively and qualitatively. The large gap between the number of possible constitutions of real-world semantics and the size of parallel data, to a large extent, restricts the model to establish the link between textual semantics and visual concepts. We alleviate this problem by augmenting the MS-COCO image captioning datasets with textual contrastive adversarial samples. These samples are synthesized using linguistic rules and the WordNet knowledge base. The construction procedure is both syntax- and semantics-aware. The samples enforce the model to ground learned embeddings to concrete concepts within the image. This simple but powerful technique brings a noticeable improvement over the baselines on a diverse set of downstream tasks, in addition to defending known-type adversarial attacks. We release the codes at https://github.com/ExplorerFreda/VSE-C.

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1806.10348")

Code

Syntology Ran 2 of 15 code samples harvested from 1 repository linked to this paper; 13 have no recorded run. Of those that ran: 2 ran · our draft was wrong.

By repository: official repository: 15 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ExplorerFreda/VSE-C officialmentioned in paperpytorchMIT 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

15 samples harvested; 2 ran; 0 honoured the contract we drafted; 13 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · our draft was wrong
13unverified

Licence: 0 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from ExplorerFreda/VSE-C. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

cosine_sim ExplorerFreda/VSE-C/VSE_C/model.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 9b0a787b92a87023 · report
from_txt ExplorerFreda/VSE-C/VSE_C/vocab.py official repository ran · our draft was wrong MIT (permissive) · ef05dda21c1cc726 · report
EncoderImage ExplorerFreda/VSE-C/VSE_C/model.py official repository unverified MIT (permissive) · 16c5b66114f6387f · report
English ExplorerFreda/VSE-C/adversarial_attack/noun.py official repository unverified MIT (permissive) · e143fe1425b0601d · report
English ExplorerFreda/VSE-C/adversarial_attack/relation.py official repository unverified MIT (permissive) · 472607bbb393c46f · report
collate_fn ExplorerFreda/VSE-C/VSE_C/data.py official repository unverified MIT (permissive) · 6961e1859e3c7fe9 · report
collate_fn_train_text ExplorerFreda/VSE-C/VSE_C/data.py official repository unverified MIT (permissive) · 1a58cc01e62897f2 · report
detect_noun_chunks ExplorerFreda/VSE-C/adversarial_attack/relation.py official repository unverified MIT (permissive) · d113e4ae72bec1ef · report
encode_data ExplorerFreda/VSE-C/VSE_C/evaluation.py official repository unverified MIT (permissive) · 5eef3e620d10d47b · report
from_flickr_json ExplorerFreda/VSE-C/VSE_C/vocab.py official repository unverified MIT (permissive) · 4d60d6b4f58a577f · report
get_paths ExplorerFreda/VSE-C/VSE_C/data.py official repository unverified MIT (permissive) · b61084903f7e3069 · report
isalpha ExplorerFreda/VSE-C/evaluation/completion/completion_datamaker.py official repository unverified MIT (permissive) · 7a8088198ac7ad87 · report
l2norm ExplorerFreda/VSE-C/VSE_C/model.py official repository unverified MIT (permissive) · 1ff2d83dc35a67ce · report
match ExplorerFreda/VSE-C/adversarial_attack/relation.py official repository unverified MIT (permissive) · 373106f951241575 · report
valid ExplorerFreda/VSE-C/adversarial_attack/noun.py official repository unverified MIT (permissive) · 4839bd92d6cdf63b · report

Tasks

Adversarial AttackImage Captioning

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