AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Graph-Propagation Based Correlation Learning for Weakly Supervised Fine-Grained Image Classification

Zhuhui Wang, Shijie Wang, Haojie Li, Zhi Dou, Jianjun Li

AAAI 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 119 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 default patches + score mechanism (ablation)ResNet-50 baseline · CUB-200-2011accuracy: 84.5% -> 86.2%Improved
add CGP criss-cross graph propagation (ablation)BL+DP+Score · CUB-200-2011accuracy: 86.2% -> 87.7%Improved
criss-cross propagation instead of same-frequency aggregation (ablation)CGP · CUB-200-2011accuracy: 87.2% -> 87.7%Improved
add CFS feature strengthening GCN (ablation)BL+DP+Score+CGP · CUB-200-2011accuracy: 87.7% -> 88.3%Improved
increase CGP depth 3 -> 4 (ablation)GCL · CUB-200-2011accuracy: 87.8% -> 87.5%Hurt
increase CFS depth 3 -> 4 (ablation)GCL · CUB-200-2011accuracy: 88.3% -> 88.1%Hurt
increase selected patches K 2 -> 4 (ablation)GCL · CUB-200-2011accuracy: 87.80% -> 88.30%Improved
GCL vs DCLfine-grained classifier · Stanford Carsaccuracy: 94.5% vs 94.0%Hurt

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