Papers › Bilinear Graph Networks for Visual Question Answering

Bilinear Graph Networks for Visual Question Answering

23 Jul 2019arXiv:1907.09815archive 2025-07-28

Dalu Guo, Chang Xu, DaCheng Tao

This paper revisits the bilinear attention networks in the visual question answering task from a graph perspective. The classical bilinear attention networks build a bilinear attention map to extract the joint representation of words in the question and objects in the image but lack fully exploring the relationship between words for complex reasoning. In contrast, we develop bilinear graph networks to model the context of the joint embeddings of words and objects. Two kinds of graphs are investigated, namely image-graph and question-graph. The image-graph transfers features of the detected objects to their related query words, enabling the output nodes to have both semantic and factual information. The question-graph exchanges information between these output nodes from image-graph to amplify the implicit yet important relationship between objects. These two kinds of graphs cooperate with each other, and thus our resulting model can model the relationship and dependency between objects, which leads to the realization of multi-step reasoning. Experimental results on the VQA v2.0 validation dataset demonstrate the ability of our method to handle the complex questions. On the test-std set, our best single model achieves state-of-the-art performance, boosting the overall accuracy to 72.41%.

PaperPDF

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

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

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

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Question Answering (VQA) GQA Test2019 GRN Accuracy 61.22 #19 of 127 Archive leaderboard report
Visual Question Answering (VQA) GQA Test2019 GRN Binary 78.69 #19 of 127 Archive leaderboard report
Visual Question Answering (VQA) GQA Test2019 GRN Consistency 90.31 #19 of 127 Archive leaderboard report
Visual Question Answering (VQA) GQA Test2019 GRN Distribution 6.77 #19 of 127 Archive leaderboard report
Visual Question Answering (VQA) GQA Test2019 GRN Open 45.81 #19 of 127 Archive leaderboard report
Visual Question Answering (VQA) GQA Test2019 GRN Plausibility 85.43 #19 of 127 Archive leaderboard report
Visual Question Answering (VQA) GQA Test2019 GRN Validity 96.36 #19 of 127 Archive leaderboard report
Visual Question Answering (VQA) VQA v2 test-std BGN, ensemble number 61.13 #15 of 38 Archive leaderboard report
Visual Question Answering (VQA) VQA v2 test-std BGN, ensemble other 66.28 #15 of 38 Archive leaderboard report
Visual Question Answering (VQA) VQA v2 test-std BGN, ensemble overall 75.92 #15 of 38 Archive leaderboard report
Visual Question Answering (VQA) VQA v2 test-std BGN, ensemble yes/no 90.89 #15 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