Research map / Label-efficient and robust learning / Recognition and long-tail
Learning Separable Fine-Grained Representation via Dendrogram Construction from Coarse Labels for Fine-grained Visual Recognition
Guanghui Shi, Xuefeng Liang, Wenjie Li, Xiaoyu Lin
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 |
|---|---|---|---|
| Use dendrogram-based BuCSFR instead of MaskCon | contrastive baseline · CIFAR100 | R@1: 71.24 -> 73.83 | Improved |
| Use BuCSFR instead of LCR | LCR · CIFAR100-hard | R@1: 63.92 -> 70.04 | Improved |
| Use BuCSFR instead of LCR | LCR · FGVC-Aircraft | R@1: 51.79 -> 57.97 | Improved |
| Use BuCSFR instead of LCR | LCR · ImageNet-1K | kNN@5: 31.01 -> 33.37 | Improved |
| Use BuCSFR instead of MaskCon, training at species level | MaskCon · iNaturalist-2019 (species) | R@5: 69.33 -> 76.84 | Improved |
| Use BuCSFR instead of MaskCon at genus level | MaskCon · iNaturalist-2019 (genus) | R@5: 91.06 -> 92.81 | Improved |
| Use BuCSFR instead of CE Fine on CIFAR10toy R@10 (gap with fine supervision) | supervised CE Fine · CIFAR10toy | R@1: 93.21 -> 97.31 | Hurt |
| Set tau_s to 0.1 rather than 0.05 (ablation) | BuCSFR · CIFAR100 | R@5: 88.49 -> 88.93 | Improved |
| Set tau_s to 0.1 rather than 0.5 (ablation) | BuCSFR · CIFAR100 | kNN@5: 77.03 -> 78.84 | Improved |
| Set tau to 0.2 rather than 0.05 (ablation) | BuCSFR · CIFAR100 | R@5: 87.18 -> 88.93 | Improved |
| Set tau to 0.2 rather than 0.5 (ablation) | BuCSFR · CIFAR100 | kNN@5: 75.42 -> 78.84 | Improved |
| Vary merging threshold T from 1.5 to 10.0 (ablation) | BuCSFR · CIFAR100 | R@5: 88.68, 88.93, 88.68, 88.53, 88.51, 88.61 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- MaskCon — MaskCon: Masked Contrastive Learning for Coarse-Labelled Dataset (CVPR 2023) · better on 8 of 8 shared results
- Grafit — Grafit: Learning Fine-Grained Image Representations With Coarse Labels (ICCV 2021) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches (ECCV 2020 · similarity 0.89)
- Free-Grained Hierarchical Visual Recognition (CVPR 2026 · similarity 0.89)
- Democratizing Fine-grained Visual Recognition with Large Language Models (ICLR 2024 · similarity 0.89)
- Fine-R1: Make Multi-modal LLMs Excel in Fine-Grained Visual Recognition by Chain-of-Thought Reasoning (ICLR 2026 · similarity 0.88)
- Fine-grained Classes and How to Find Them (ICML 2024 · similarity 0.88)
- Advancing Fine-Grained Classification by Structure and Subject Preserving Augmentation (NeurIPS 2024 · similarity 0.88)
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.
