AI Paper Atlas

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

Trusted Fine-Grained Image Classification through Hierarchical Evidence Fusion

Zhikang Xu, Xiaodong Yue, Ying Lv, Wei Liu, Zihao Li

AAAI 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Group-robust classification · 18 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 hierarchical evidence fusion to ME + NR + SUM (ablation)Trusted FGIC · CUB-200-2011accuracy: 88.6% to 89.3%Improved
Add hierarchical evidence fusion to ME + R + USUM (ablation)Trusted FGIC · CUB-200-2011accuracy: 89.3% to 89.9%Improved
Use uncertainty-based expert combination instead of SUM, with expert reduction (ablation)Trusted FGIC · CUB-200-2011accuracy: 88.6% to 89.3%Improved
Fuse hierarchical classification evidence at test timeTrusted FGIC · FGVC-Aircraftaccuracy: +0.5%Improved
Fuse hierarchical classification evidence at test timeTrusted FGIC · Stanford Carsaccuracy: 94.9 vs 95.1Hurt

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