AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Fine-Grained Visual Entailment

Christopher Thomas, Yipeng Zhang, Shih-Fu Chang

ECCV 2022 · Vision-language and multimodal › Multimodal LLMs · approach: Instruction-tuned multimodal assistants · 7 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
lower beta_CLS from 1 to 0.5 (ablation)Ours (KE classifier) · Fine-grained VE (KE classifier only)Acc_KE->CLS (relabeled): 67.77 -> 80.73Improved
lower beta_CLS from 1 to 0.5 (ablation)Ours (KE classifier) · Fine-grained VE (KE classifier only)Acc_KE: 58.75 -> 68.07Improved
lower beta_CLS from 1 to 0.5 (ablation)Ours (KE classifier) · Fine-grained VE (KE classifier only)Acc_con: 30.85 -> 62.76Improved
lower beta_CLS further from 0.5 to 0.1 (ablation)Ours (KE classifier) · Fine-grained VE (KE classifier only)Acc_con: 62.76 -> 44.68Hurt
lower beta_CLS further from 0.5 to 0.1 (ablation)Ours (KE classifier) · Fine-grained VE (KE classifier only)Acc_KE->CLS (relabeled): 80.73 -> 75.41Hurt
lower beta_CLS further from 0.5 to 0.1 (ablation)Ours (KE classifier) · Fine-grained VE (KE classifier only)Acc_KE: 68.07 -> 68.30No clear effect
add the structural loss (beta_STRUC 0 -> 1) (ablation)Ours (KE classifier) · Fine-grained VE (KE classifier only)Acc_STRUC: 70.26 -> 96.36Improved
add the structural loss (beta_STRUC 0 -> 1) (ablation)Ours (KE classifier) · Fine-grained VE (KE classifier only)Acc_con: 9.57 -> 62.76Improved
add the structural loss (beta_STRUC 0 -> 1) (ablation)Ours (KE classifier) · Fine-grained VE (KE classifier only)Acc_neu: 15.48 -> 31.29Improved
add the structural loss (beta_STRUC 0 -> 1) (ablation)Ours (KE classifier) · Fine-grained VE (KE classifier only)Acc_ent: 88.87 -> 79.64Hurt
raise beta_KE from 0.5 to 1 (ablation)Ours (KE classifier) · Fine-grained VE (KE classifier only)Acc_KE: 61.68 -> 68.07Improved
raise beta_KE from 0.5 to 1 (ablation)Ours (KE classifier) · Fine-grained VE (KE classifier only)Acc_STRUC: 98.40 -> 96.36Hurt

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