paper-with-me

홈 › Papers

Modulating early visual processing by language

2017-07-02 · NeurIPS 2017 12 · 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.

📄 PDF Abstract BibTeX arXiv:1707.00683

Code (2)

GuessWhatGame/clevr tf
ap229997/Conditional-Batch-Norm pytorch

Tasks

Question AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Methods 이 논문이 사용한 방법론

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
Feedforward Network A Feedforward Network, or a Multilayer Perceptron (MLP), is a neural network with solely densely connected layers. This is the classic neural network architecture of the…
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
Adam 설명 없음
MODERN 설명 없음
Conditional Batch Normalization Conditional Batch Normalization (CBN) is a class-conditional variant of batch normalization. The key idea is to…

Similar Papers 제목 키워드 기반

Modulation of early visual processing alleviates capacity limits in solving multiple tasks

2019-07-29 · Sushrut Thorat, Giacomo Aldegheri, Marcel A. J. van Gerven, Marius V. Peelen

In daily life situations, we have to perform multiple tasks given a visual stimulus, which requires task-relevant information to be transmitted through our visual system. When it is not possible to transmit all the possi…

object-detectionObject Detection

Language Controls More Than Top-Down Attention: Modulating Bottom-Up Visual Processing with Referring Expressions

2021-01-01 · Ozan Arkan Can, Ilker Kesen, Deniz Yuret

How to best integrate linguistic and perceptual processing in multimodal tasks is an important open problem. In this work we argue that the common technique of using language to direct visual attention over high-level vi…

Referring Expression

Modulating Bottom-Up and Top-Down Visual Processing via Language-Conditional Filters

2020-03-28 · İlker Kesen, Ozan Arkan Can, Erkut Erdem, Aykut Erdem 외

How to best integrate linguistic and perceptual processing in multi-modal tasks that involve language and vision is an important open problem. In this work, we argue that the common practice of using language in a top-do…

ColorizationImage ColorizationReferring ExpressionReferring Expression Segmentation+1

Should We Attend More or Less? Modulating Attention for Fairness

2023-05-22 · Abdelrahman Zayed, Goncalo Mordido, Samira Shabanian, Sarath Chandar

The advances in natural language processing (NLP) pose both opportunities and challenges. While recent progress enables the development of high-performing models for a variety of tasks, it also poses the risk of models l…

Fairnesstext-classificationText Classification

V-SEAM: Visual Semantic Editing and Attention Modulating for Causal Interpretability of Vision-Language Models

2025-09-18 · Qidong Wang, Junjie Hu, Ming Jiang arxiv

Recent advances in causal interpretability have extended from language models to vision-language models (VLMs), seeking to reveal their internal mechanisms through input interventions. While textual interventions often t…