AI Paper Atlas

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

Multi-Modal Answer Validation for Knowledge-Based VQA

Jialin Wu, Jiasen Lu, Ashish Sabharwal, Roozbeh Mottaghi

AAAI 2022 · Vision-language and multimodal › Visual question answering · approach: Universal VQA models · 115 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
Use answer-guided retrieval from Wikipedia and ConceptNetMAVEx on ViLBERT · OK-VQA v1.1 testVQA soft score: 39.45Improved
Add Google Images as a knowledge source to Wikipedia and ConceptNet (ablation)MAVEx · OK-VQA v1.1 testVQA soft score: 39.45 -> 40.28Improved
Add answer validation to the retrieved-knowledge model (ablation)MAVEx · OK-VQA v1.1 testVQA soft score: 39.2 to 40.28Improved
Add Wikipedia sentence decontextualization (ablation)MAVEx with Wikipedia knowledge · OK-VQA v1.1 testVQA soft score: 38.21 -> 38.63Improved
Add ConceptNet to Wikipedia knowledge (ablation)MAVEx · OK-VQA v1.1 testVQA soft score: 38.63 -> 39.45Improved
Add images to ConceptNet knowledge (ablation)MAVEx · OK-VQA v1.1 testVQA soft score: 38.56 -> 39.60Improved
Add images to Wikipedia knowledge (ablation)MAVEx · OK-VQA v1.1 testVQA soft score: 38.63 -> 39.37Improved
Add Wikipedia to ConceptNet and images (ablation)MAVEx · OK-VQA v1.1 testVQA soft score: 39.60 -> 40.28Improved
Add ConceptNet to Wikipedia and images (ablation)MAVEx · OK-VQA v1.1 testVQA soft score: 39.37 -> 40.28Improved
Replace noun-phrase-level multi-head attention with average pooling (ablation)MAVEx · OK-VQA v1.1 testVQA soft score: 39.77Hurt
Replace question-level multi-head attention with average pooling (ablation)MAVEx · OK-VQA v1.1 testVQA soft score: 39.60Hurt
Expand the answer candidate set from top 5 to top 6ViLBERT candidate generation · OK-VQA testVQA soft score of best answer in candidate set: 59.7 -> 62.1Improved

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