AI Paper Atlas

Research map / Probabilistic and scientific modeling / Causal discovery

A Reverse Causal Framework to Mitigate Spurious Correlations for Debiasing Scene Graph Generation

Shuzhou Sun, Li Liu, Tianpeng Liu, Shuaifeng Zhi, Ming‐Ming Cheng, Janne Heikkilä, Yongxiang Liu

TPAMI 2025 · Probabilistic and scientific modeling › Causal discovery · approach: Latent-variable causal estimation · 7 citations (OpenAlex)

Read the paper

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 RcSGG reverse causal trainingMotifsNet · VG150 PredClsmR@100: 16.8 -> 41.4Improved
add RcSGG reverse causal trainingVCTree · VG150 SGClsmR@100: 8.0 -> 29.6Improved
add RcSGG reverse causal trainingTransformer · VG150 SGDetmR@100: 8.8 -> 20.9Improved
add RcSGG reverse causal trainingMotifsNet · GQA PredClsmR@100: 16.3 -> 38.5Improved
add RcSGG reverse causal trainingVCTree · GQA SGDetmR@100: 7.4 -> 18.3Improved
use RcSGG instead of FGPL-AMotifsNet · VG150 PredClsmR@100: 42.4 -> 41.4Hurt
use RcSGG instead of FGPL-ATransformer · VG150 PredClsmR@50: 36.3 -> 39.6Improved
use RcSGG instead of GCLMotifsNet · GQA SGDetmR@100: 18.8 -> 17.6Hurt

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