AI Paper Atlas

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

VLGrammar: Grounded Grammar Induction of Vision and Language

Yining Hong, Qing Li, Song-Chun Zhu, Siyuan Huang

ICCV 2021 · Vision-language and multimodal › Human and embodied modeling · approach: Language-grounded scene text and structure · 18 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 SCAN pretraining of the part clustering module (ablation)VLGrammar · PartIt image grammar (all categories)corpus-level F1 / instance-level F1: 44.7 -> 51.4 corpus, 55.5 -> 63.4 instanceImproved
add SCAN pretraining of the part clustering module (ablation)VLGrammar · PartIt part clustering (all categories)accuracy: 64.4 -> 69.1Improved
add SCAN pretraining of the part clustering module (ablation)VLGrammar · PartIt image grammar (table)corpus-level F1 / instance-level F1: 57.9 -> 46.3 corpus, 75.4 -> 60.5 instanceHurt
add SCAN pretraining of the part clustering module (ablation)VLGrammar · PartIt language grammar (all categories)corpus-level F1 / instance-level F1: 49.0 -> 51.3 corpus, 49.8 -> 51.9 instanceNo clear effect
train image grammar jointly with language grammar (VLGrammar vs V-PCFG)V-PCFG · PartIt part clustering (all categories)accuracy: 41.3 -> 69.1 (SCAN to VLGrammar)Improved
joint contrastive training of vision and language grammars (vs V-PCFG)V-PCFG · PartIt image grammar (all categories)corpus-level F1: 47.5 -> 51.4Improved
joint training vs language grounding only (vs L-PCFG)L-PCFG · PartIt language grammar (all categories)corpus-level F1: 48.4 -> 51.3Improved
pretrain a category-agnostic language PCFG then fine-tune per categoryL-PCFG · PartIt language grammar (all categories)corpus-level F1: 47.8 -> 48.4Improved
add grammar induction to a ResNet-18/BERT retrieval modelretrieval baseline · PartIt image-text retrieval (chair)text-to-image accuracy: 24.1 -> 33.2 IR, 28.5 -> 39.0 TRImproved
add grammar induction to a ResNet-18/BERT retrieval modelretrieval baseline · PartIt image-text retrieval (bed)text-to-image accuracy: 20.1 -> 39.6 IR, 20.1 -> 38.2 TRImproved
use language-grounded training (V-PCFG-LG) vs VLGrammar on unseen categoriesV-PCFG-LG · PartIt unseen category bed (trained on chair+table)instance-level F1: 50.4 -> 44.2Hurt
train image grammar on chair+table and test on unseen categoryVLGrammar · PartIt unseen category bedcorpus-level F1: 20.7 -> 29.4 (V-PCFG to VLGrammar)Improved

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