Research map / Label-efficient and robust learning / Recognition and long-tail
Solving Long-tailed Recognition with Deep Realistic Taxonomic Classifier
Tz-Ying Wu, Pedro Morgado, Pei Wang, Chih-Hui Ho, Nuno Vasconcelos
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 changed | Where | Measured | Effect |
|---|---|---|---|
| replace Softmax with Deep-RTC | iNaturalist classifier · iNaturalist 2018 (all classes) | CPB: 0.66 -> 0.78 | Improved |
| replace Softmax with Deep-RTC | few-shot classes on iNaturalist · iNaturalist 2018 (few-shot classes) | CPB: 0.62 -> 0.75 | Improved |
| replace Softmax with Deep-RTC | many-shot classes on iNaturalist · iNaturalist 2018 (many-shot classes) | CPB: 0.76 -> 0.84 | Improved |
| use CBLoss instead of Softmax | iNaturalist classifier · iNaturalist 2018 (many-shot classes) | CPB: 0.76 -> 0.61 | Hurt |
| use tau-norm instead of Softmax | iNaturalist classifier · iNaturalist 2018 (many-shot classes) | CPB: 0.76 -> 0.71 | Hurt |
| replace Softmax with Deep-RTC | ImageNet-LT classifier · ImageNet-LT | CPB: 0.35 -> 0.53 | Improved |
| replace flat realistic predictor with Deep-RTC at 20% rejection | CIFAR100-LT · CIFAR100-LT, 20% rejection (all classes) | CPB: .433 -> .491 | Improved |
| replace flat realistic predictor with Deep-RTC at 5% rejection | AWA2-LT · AWA2-LT, 5% rejection (all classes) | CPB: .914 -> .931 | Improved |
| replace flat realistic predictor with Deep-RTC on many-shot classes at 5% rejection | CIFAR100-LT · CIFAR100-LT, 5% rejection (many-shot classes) | CPB: .779 -> .773 | No clear effect |
| add stochastic tree sampling and node-consistency loss to parameter inheritance (Deep-RTC) (ablation) | recursive hierarchical classifier · iNaturalist-sub | CPB | Improved |
| add stochastic tree sampling (global) instead of node-consistency loss (local) (ablation) | parameter-inheritance classifier · iNaturalist-sub | CPB | Improved |
| use bottom-up hierarchical inference (RHC) instead of flat softmax (ablation) | flat classifier · iNaturalist-sub | CPB | Improved |
Closest papers by meaning
- Deep Long-Tailed Learning: A Survey (TPAMI 2023 · similarity 0.86)
- Feature Fusion from Head to Tail for Long-Tailed Visual Recognition (AAAI 2024 · similarity 0.85)
- Decoupling Representation and Classifier for Long-Tailed Recognition (ICLR 2020 · similarity 0.85)
- Long-Tailed Recognition via Information-Preservable Two-Stage Learning (NeurIPS 2025 · similarity 0.85)
- DiffuLT: Diffusion for Long-tail Recognition Without External Knowledge (NeurIPS 2024 · similarity 0.84)
- LTGC: Long-tail Recognition via Leveraging LLMs-driven Generated Content (CVPR 2024 · 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.
