Papers › Modulating early visual processing by language

Modulating early visual processing by language

2 Jul 2017NeurIPS 2017 12arXiv:1707.00683archive 2025-07-28

Harm de Vries, Florian Strub, Jérémie Mary, Hugo Larochelle, Olivier Pietquin, Aaron Courville

It is commonly assumed that language refers to high-level visual concepts while leaving low-level visual processing unaffected. This view dominates the current literature in computational models for language-vision tasks, where visual and linguistic input are mostly processed independently before being fused into a single representation. In this paper, we deviate from this classic pipeline and propose to modulate the \emph{entire visual processing} by linguistic input. Specifically, we condition the batch normalization parameters of a pretrained residual network (ResNet) on a language embedding. This approach, which we call MOdulated RESnet (\MRN), significantly improves strong baselines on two visual question answering tasks. Our ablation study shows that modulating from the early stages of the visual processing is beneficial.

PaperPDFConference PDFCode

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

Code

GuessWhatGame/clevr mentioned on GitHubtf report
ap229997/Conditional-Batch-Norm mentioned on GitHubpytorch 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Question AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: Conditional Batch Normalization

1x1 ConvolutionAdamAverage PoolingBatch NormalizationBottleneck Residual BlockConditional Batch NormalizationConvolutionDense ConnectionsFeedforward NetworkGlobal Average PoolingKaiming InitializationLSTMMODERNMax PoolingReLUResidual BlockResidual ConnectionSigmoid ActivationTanh Activation

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