AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

Reducing Language Biases in Visual Question Answering with Visually-Grounded Question Encoder

Gouthaman KV, Anurag Mittal

ECCV 2020 · Vision-language and multimodal › Visual question answering · approach: Attention and prior-robust VQA · 85 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace the GRU question encoder with VGQEBaseline (RUBi base model) · VQA-CPv2 testoverall accuracy: 38.46 -> 50.11Improved
replace the GRU question encoder with VGQEUpDn · VQA-CPv2 testoverall accuracy: 39.74 -> 48.75Improved
replace the GRU question encoder with VGQEBAN · VQA-CPv2 testoverall accuracy: 39.31 -> 50.0Improved
replace the GRU question encoder with VGQEUpDn · VQAv2 valoverall accuracy: 63.48 -> 64.04Improved
replace the GRU question encoder with VGQEBaseline (RUBi base model) · VQAv2 valoverall accuracy: 63.10 -> 63.18No clear effect
replace the GRU question encoder with VGQEBAN · VQAv2 valoverall accuracy: 65.36 -> 65.73Improved
add RUBi question-only branchBaseline · VQAv2 valoverall accuracy: 63.10 -> 61.16Hurt
add RUBi question-only branchBaseline · VQA-CPv2 testoverall accuracy: 38.46 -> 47.11Improved
add LangAtt debiasingUpDn · VQAv2 valoverall accuracy: 63.48 -> 57.96Hurt
add SCR with extra human attention annotationsUpDn · VQAv2 valoverall accuracy: 63.48 -> 62.2Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy