Research map / Label-efficient and robust learning / Recognition and long-tail
Label Relation Graphs Enhanced Hierarchical Residual Network for Hierarchical Multi-Granularity Classification
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 granularity-specific blocks to the trunk and combinatorial loss (ablation) | HRN · CUB-200-2011, species, 0% relabeling | OA: 84.32 -> 85.77 | Helped |
| Add linear combination of hierarchical features (ablation) | HRN with GSB · CUB-200-2011, species, 0% relabeling | OA: 85.77 -> 86.17 | Helped |
| Add ReLU after combining hierarchical features (ablation) | HRN with GSB and LC · CUB-200-2011, species, 0% relabeling | OA: 86.17 -> 86.60 | Helped |
| Add leaf-level multi-class cross-entropy to the hierarchical probabilistic loss (ablation) | Combinatorial loss · CUB-200-2011, species, 0% relabeling | OA: 84.56 -> 86.60 | Helped |
| Add leaf-level multi-class cross-entropy to the hierarchical probabilistic loss (ablation) | Combinatorial loss · CUB-200-2011, species, 90% relabeling | OA: 28.69 -> 53.02 | Helped |
| Use the proposed method rather than Chang et al. | CUB-200-2011 · 90% relabeling, species | OA: 49.36 -> 53.02 | Helped |
| Use the proposed method rather than HMC-LMLP | Aircraft · 90% relabeling, model | OA: 74.41 -> 71.06 | Hurt |
| Use the proposed method rather than Chang et al. | Stanford Cars · 90% relabeling, maker | OA: 45.79 -> 49.30 | Helped |
Closest papers by meaning
- Hierarchical Multi-Label Classification Networks (ICML 2018 · similarity 0.88)
- Hierarchical Granularity Transfer Learning (NeurIPS 2020 · similarity 0.86)
- Self-Paced Unified Representation Learning for Hierarchical Multi-Label Classification (AAAI 2024 · similarity 0.85)
- Coherent Hierarchical Multi-Label Classification Networks (NeurIPS 2020 · similarity 0.85)
- Bidirectional Logits Tree: Pursuing Granularity Reconcilement in Fine-Grained Classification (AAAI 2025 · similarity 0.84)
- MLC-NC: Long-Tailed Multi-Label Image Classification Through the Lens of Neural Collapse (AAAI 2025 · similarity 0.83)
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.