AI Paper Atlas

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

Compositional Substitutivity of Visual Reasoning for Visual Question Answering

Chuanhao Li, Zhen Li, Chenchen Jing, Yuwei Wu, Mingliang Zhai, Yunde Jia

ECCV 2024 · Vision-language and multimodal › Visual question answering · approach: Universal VQA models · 0 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
add SUPS support-set training frameworkMAC · GQA-SPS Word SPSConsistency: 47.5 -> 55.6Improved
add SUPS to five VQA baselinesViLT, mPLUG, BEiT-3, MAC, LXMERT · GQA-SPS HM consistencyHM Consistency: LXMERT 65.5 -> 67.3; BEiT-3 65.3 -> 66.2Improved
add SUPS to baselines on in-distribution GQABEiT-3 · GQA test-devAccuracy: 60.8 -> 61.8Improved
add SUPS to MAC on in-distribution GQAMAC · GQA test-devAccuracy: 53.1 -> 53.5No clear effect
add SUPS to LXMERT on VQA-RephrasingsLXMERT · VQA-RephrasingsCS(4): 60.03 -> 60.93Improved
use support sets for plain data augmentation instead of reconstruction (ablation)LXMERT · GQA-SPSConsistency (Word / Visual Entity / Referent): Visual Entity 73.30 -> 69.83 (DA question), Referent 56.63 -> 55.62Hurt
build support sets from same-batch samples (OSB) instead of back-translation and retrieval (ablation)LXMERT · GQA-SPSConsistency: SUPS Word 71.43 vs OSB 69.57Hurt
use both question and image support sets (ablation)LXMERT+SUPS · GQA-SPSConsistency: Referent 58.26 -> 58.39Improved
increase sampled support number K above 10 (ablation)LXMERT+SUPS · GQA-SPSHM ConsistencyHurt
scale up to large vision-language models in zero-shotCogVLM, LLaVA and others · GQA-SPSHM Consistency: CogVLM 57.7 vs LXMERT 65.5No clear effect

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