SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1906.08430 · 2019

Adversarial Regularization for Visual Question Answering: Strengths, Shortcomings, and Side Effects

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/1906.08430.json · badge: /api/ran/1906.08430.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
gabegrand/adversarial-vqa canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
2 ran · 0 no recorded run
FunctionStatusWhere it lives
extract_bboxes Ran
ran; our contract draft was wrong, not the code
gabegrand/adversarial-vqa/tools/extract_features.py
pointer only (licence: NOASSERTION) · get_code("6ba35b3c72ee9bd5")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, gabegrand/adversarial-vqa (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

parse_annotation Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from sameerdharur/sorting-vqa
pointer only; the stored copy get_code serves, from sameerdharur/sorting-vqa, is pointer only (licence: NOASSERTION) · get_code("099456faba640847")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

parse_ans Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from sameerdharur/sorting-vqa
pointer only; the stored copy get_code serves, from sameerdharur/sorting-vqa, is pointer only (licence: NOASSERTION) · get_code("2d308ec5cf958c0f")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 2 later) and 1 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
parse_annotation 2 other papers
1 dated earlier, 1 later
1807.09956 (2018-07)
Pythia v0.1: the Winning Entry to the VQA Challenge 2018
2010.10038 (2020-10)
SOrT-ing VQA Models : Contrastive Gradient Learning for Improved Consistency
parse_ans 2 other papers
1 dated earlier, 1 later
1807.09956 (2018-07)
Pythia v0.1: the Winning Entry to the VQA Challenge 2018
2010.10038 (2020-10)
SOrT-ing VQA Models : Contrastive Gradient Learning for Improved Consistency

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Visual question answering (VQA) models have been shown to over-rely on linguistic biases in VQA datasets, answering questions "blindly" without considering visual context. Adversarial regularization (AdvReg) aims to address this issue via an adversary sub-network that encourages the main model to learn a bias-free representation of the question. In this work, we investigate the strengths and shortcomings of AdvReg with the goal of better understanding how it affects inference in VQA models. Despite achieving a new state-of-the-art on VQA-CP, we find that AdvReg yields several undesirable side-effects, including unstable gradients and sharply reduced performance on in-domain examples. We demonstrate that gradual introduction of regularization during training helps to alleviate, but not completely solve, these issues. Through error analyses, we observe that AdvReg improves generalization to binary questions, but impairs performance on questions with heterogeneous answer distributions. Qualitatively, we also find that regularized models tend to over-rely on visual features, while ignoring important linguistic cues in the question. Our results suggest that AdvReg requires further refinement before it can be considered a viable bias mitigation technique for VQA.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1906.08430")
get_code_for_paper("1906.08430")
have("1906.08430")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1906.08430.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1906.08430.svg)](https://syntology.ai/paper/1906.08430)

Connect an agent — have() is free.