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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Add hierarchical evidence fusion to ME + NR + SUM (ablation) | Trusted FGIC · CUB-200-2011 | accuracy: 88.6% to 89.3% | Improved |
| Add hierarchical evidence fusion to ME + R + USUM (ablation) | Trusted FGIC · CUB-200-2011 | accuracy: 89.3% to 89.9% | Improved |
| Use uncertainty-based expert combination instead of SUM, with expert reduction (ablation) | Trusted FGIC · CUB-200-2011 | accuracy: 88.6% to 89.3% | Improved |
| Fuse hierarchical classification evidence at test time | Trusted FGIC · FGVC-Aircraft | accuracy: +0.5% | Improved |
| Fuse hierarchical classification evidence at test time | Trusted FGIC · Stanford Cars | accuracy: 94.9 vs 95.1 | Hurt |
Closest papers by meaning
- Fine-grained Classes and How to Find Them (ICML 2024 · similarity 0.86)
- Cross-Layer and Cross-Sample Feature Optimization Network for Few-Shot Fine-Grained Image Classification (AAAI 2024 · similarity 0.86)
- Few-Shot Fine-Grained Image Classification with Progressively Feature Refinement and Continuous Relationship Modeling (AAAI 2025 · similarity 0.85)
- Hierarchical Novelty Detection via Fine-Grained Evidence Allocation (ICML 2024 · similarity 0.84)
- Advancing Fine-Grained Classification by Structure and Subject Preserving Augmentation (NeurIPS 2024 · similarity 0.84)
- Twofold Debiasing Enhances Fine-Grained Learning with Coarse Labels (AAAI 2025 · similarity 0.84)
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.
