AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Interpretable Visual Reasoning via Induced Symbolic Space

Zhonghao Wang, Kai Wang, Mo Yu, Jinjun Xiong, Wen-mei Hwu, Mark Hasegawa-Johnson, Humphrey Shi

ICCV 2021 · Vision-language and multimodal › Human and embodied modeling · approach: Abstract visual reasoning benchmarks · 19 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
increase MAC reasoning steps from 4 to 8 (ablation)OCCAM · CLEVRaccuracy: 94.3 -> 98.6Improved
increase MAC reasoning steps from 8 to 12 (ablation)OCCAM · CLEVRaccuracy: 98.6 -> 99.4Improved
increase MAC reasoning steps from 12 to 16 (ablation)OCCAM · CLEVRaccuracy: 99.4 -> 99.1No clear effect
increase MAC reasoning steps from 4 to 16 (ablation)OCCAM · GQA test-devaccuracy: 55.1 -> 56.2Improved
use learnable ResNet34 object features instead of pretrained ResNet101 (ablation)OCCAM · CLEVR valaccuracy: 97.9% -> 99.0%Improved
add global features to learnable ResNet34 object features (ablation)OCCAM · CLEVR valaccuracy: 99.0% -> 99.4%Improved
constrain attention to object-level features instead of image-level attentionMAC · CLEVR and GQA validation setsaccuracyImproved
replace visual features with induced symbolic conceptsOCCAM · CLEVR and GQAaccuracyNo clear effect
use induced concept correlations instead of word2vec embeddings for synonym classificationword concept grouping · Human study synonyms/uncorrelated wordsoverall accuracy: 68.37% -> 78.06%Improved
use induced concept proximity instead of GloVe embeddings for word rankingword concept grouping · Word proximity ranking vs humanKendall tau ranking distance: 0.3418 -> 0.2585Improved

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