AI Paper Atlas

Research map / Probabilistic and scientific modeling / Causal discovery

A Causal Adjustment Module for Debiasing Scene Graph Generation

Li Liu, Shuzhou Sun, Shuaifeng Zhi, Fan Shi, Zhen Liu, Janne Heikkilä, Yongxiang Liu

TPAMI 2025 · Probabilistic and scientific modeling › Causal discovery · approach: Latent-variable causal estimation · 47 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 CAModuleMotifsNet · VG150 PredClsmR@100: 16.8 -> 39.3Improved
add CAModuleMotifsNet · VG150 SGClsmR@100: 9.5 -> 24.7Improved
add CAModuleMotifsNet · VG150 SGDetmR@100: 8.5 -> 18.2Improved
add CAModuleVCTree · VG150 PredClsmR@100: 16.6 -> 40.5Improved
add CAModuleVCTree · VG150 SGClsmR@100: 8.0 -> 25.9Improved
add CAModuleTransformer · VG150 PredClsmR@100: 17.5 -> 39.4Improved
add CAModuleTransformer · VG150 SGDetmR@100: 8.8 -> 19.3Improved
add CAModuleMotifsNet · GQA PredClsmR@100: 16.3 -> 38.7Improved
add CAModuleTransformer · GQA PredClsmR@100: 17.7 -> 40.2Improved
use CAModule instead of GCL as debiasing methodMotifsNet · VG150 SGDetmR@100: 19.3 -> 18.2Hurt
use CAModule instead of FGPL as debiasing methodVCTree · VG150 SGClsmR@100: 27.6 -> 25.9Hurt
use CAModule instead of GCL as debiasing methodMotifsNet · VG150 PredClsmR@100: 38.2 -> 39.3Improved

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