• Home
  • Search
  • In Defense of Grid Features for Visual Question Answering
  • Open Access IconOpen Access
  • Cite Icon388
  • https://doi.org/10.1109/cvpr42600.2020.01028Copy DOI Icon

In Defense of Grid Features for Visual Question Answering

  • Jun 1, 2020
  • Huaizu Jiang +4 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Popularized as `bottom-up' attention, bounding box (or region) based visual features have recently surpassed vanilla grid-based convolutional features as the de facto standard for vision and language tasks like visual question answering (VQA). However, it is not clear whether the advantages of regions (e.g. better localization) are the key reasons for the success of bottom-up attention. In this paper, we revisit grid features for VQA, and find they can work surprisingly well -- running more than an order of magnitude faster with the same accuracy (e.g. if pre-trained in a similar fashion). Through extensive experiments, we verify that this observation holds true across different VQA models (reporting a state-of-the-art accuracy on VQA 2.0 test-std, 72.71), datasets, and generalizes well to other tasks like image captioning. As grid features make the model design and training process much simpler, this enables us to train them end-to-end and also use a more flexible network design. We learn VQA models end-to-end, from pixels directly to answers, and show that strong performance is achievable without using any region annotations in pre-training. We hope our findings help further improve the scientific understanding and the practical application of VQA. Code and features will be made available.

Similar Papers
  • Research Article
  • Citations1

Adversarial Sample Synthesis for Visual Question Answering

  • Nov 21, 2024
  • ACM Transactions on Multimedia Computing, Communications, and Applications
  • Chuanhao Li +4
  • PDF
  • Conference Article
  • Citations2

Can Pre-training help VQA with Lexical Variations?

  • Jan 01, 2020
  • Shailza Jolly +1
  • PDF
  • Conference Article
  • Citations26

Decoupled Box Proposal and Featurization with Ultrafine-Grained Semantic Labels Improve Image Captioning and Visual Question Answering

  • Jan 01, 2019
  • Soravit Changpinyo +3
  • Research Article
  • Citations42

Knowledge-Routed Visual Question Reasoning: Challenges for Deep Representation Embedding.

  • Jan 01, 2021
  • IEEE Transactions on Neural Networks and Learning Systems
  • Qingxing Cao +4
  • Conference Article
  • Citations668

Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering

  • Jun 01, 2018
  • Aishwarya Agrawal +3
  • Research Article
  • Citations33

Causal Inference with Knowledge Distilling and Curriculum Learning for Unbiased VQA

  • Mar 04, 2022
  • ACM Transactions on Multimedia Computing, Communications, and Applications
  • Yonghua Pan +3
  • Book Chapter

Boosting Visual Question Answering Through Geometric Perception and Region Features

  • Sep 28, 2023
  • Frontiers in artificial intelligence and applications
  • Hong Yu +3
  • Research Article
  • Citations503

Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering

  • Sep 11, 2018
  • International Journal of Computer Vision
  • Yash Goyal +5
  • PDF
  • Conference Article
  • Citations16

VQA-MHUG: A Gaze Dataset to Study Multimodal Neural Attention in Visual Question Answering

  • Jan 01, 2021
  • Ekta Sood +4
  • PDF
  • Research Article
  • Citations19

Advancing surgical VQA with scene graph knowledge

  • May 23, 2024
  • International Journal of Computer Assisted Radiology and Surgery
  • Kun Yuan +5
  • Book Chapter
  • Citations5

Neural Networks for Detecting Irrelevant Questions During Visual Question Answering

  • Jan 01, 2020
  • Mengdi Li +2
  • Conference Article
  • Citations47

Quantifying and Alleviating the Language Prior Problem in Visual Question Answering

  • Jul 18, 2019
  • Yangyang Guo +5
  • Research Article

Visual Question Answering Model Using Transformer-Based Multi-Head Cross Attention Network with Optimized Gold Rush Octave Convolution Network

  • Oct 28, 2025
  • International Journal of Image and Graphics
  • J Jinu Sophia +2
  • Research Article
  • Citations2

VADS: Visuo-Adaptive DualStrike attack on visual question answer

  • Aug 31, 2024
  • Computer Vision and Image Understanding
  • Boyuan Zhang +4
  • Conference Article
  • Citations7

Unleashing the Potential of Large Language Model: Zero-shot VQA for Flood Disaster Scenario

  • Nov 17, 2023
  • Yimin Sun +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.