Papers › In Defense of Grid Features for Visual Question Answering

In Defense of Grid Features for Visual Question Answering

10 Jan 2020CVPR 2020 6arXiv:2001.03615archive 2025-07-28

Huaizu Jiang, Ishan Misra, Marcus Rohrbach, Erik Learned-Miller, Xinlei Chen

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.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

Code

clip-vil/CLIP-ViL mentioned on GitHubpytorch report
facebookresearch/grid-feats-vqa mentioned on GitHubpytorchApache-2.0 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

Image CaptioningQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Question Answering (VQA) VQA v2 test-dev X-101 grid features + MCAN Accuracy 72.59 #22 of 56 Archive leaderboard report
Visual Question Answering (VQA) VQA v2 test-std Single, w/o VLP number 58.01 #17 of 38 Archive leaderboard report
Visual Question Answering (VQA) VQA v2 test-std Single, w/o VLP other 64.77 #17 of 38 Archive leaderboard report
Visual Question Answering (VQA) VQA v2 test-std Single, w/o VLP overall 74.16 #17 of 38 Archive leaderboard report
Visual Question Answering (VQA) VQA v2 test-std Single, w/o VLP yes/no 89.18 #17 of 38 Archive leaderboard report
Visual Question Answering (VQA) VQA v2 test-std X-101 grid features + MCAN overall 72.71 #20 of 38 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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