AI Paper Atlas

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

Linguistically Routing Capsule Network for Out-of-Distribution Visual Question Answering

Qingxing Cao, Wentao Wan, Keze Wang, Xiaodan Liang, Liang Lin

ICCV 2021 · Vision-language and multimodal › Visual question answering · approach: Attention and prior-robust VQA · 16 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 linguistically routing (unary + binary + parser) to a regular network (ablation)FiLM-based baseline · CLEVR-CoGenT val (trained on condition A) condition Baccuracy: 78.19 -> 85.58Improved
add linguistic routing (ablation)MCAN-based baseline · VQA-CP v2 testaccuracy: 51.15 -> 52.18Improved
add unary routing only (binary potential 0) (ablation)no-routing baseline · CLEVR-CoGenT val (trained on condition A) condition Baccuracy: 78.19 -> 82.17Improved
add binary potential 1 on top of unary routing (ablation)LR-Capsule with unary only · CLEVR-CoGenT val (trained on condition A) condition Baccuracy: 82.17 -> 85.58Improved
raise binary potential from 1 to 2 (ablation)LR-Capsule · CLEVR-CoGenT val (trained on condition A) condition Baccuracy: 85.58 -> 79.16Hurt
raise binary potential from 0 to 0.5 (ablation)LR-Capsule · CLEVR-CoGenT val (trained on condition A) condition Baccuracy: 82.17 -> 82.25No clear effect
add parser-guided binary potential instead of learned binary potential (ablation)LR-Capsule with unary+binary · CLEVR-CoGenT val (trained on condition A) condition Baccuracy: 78.29 -> 85.58Improved
keep softmax-normalized single unary value instead of removing normalization (+scale) (ablation)LR-Capsule · CLEVR-CoGenT val (trained on condition A) condition Baccuracy: 81.73 -> 85.58Improved
use single unary value instead of elementwise multiplicative vector (+mul) (ablation)LR-Capsule · CLEVR-CoGenT val (trained on condition A) condition Baccuracy: 78.01 -> 82.17Improved
add LR-Capsule to RUBi on VQA-CP v2RUBi · VQA-CP v2 testaccuracy: 47.11 -> 52.19Improved
add linguistic routing to MCAN on VQA v2 valMCAN · VQA v2 valaccuracy: 67.2 -> 67.04No clear effect
replace LMH ensemble with LR-Capsule on Number questionsLMH · VQA-CP v2 testaccuracy (Number): 44.46 -> 28.37Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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