Research map / Label-efficient and robust learning / Recognition and long-tail
Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches
Ruoyi Du, Dongliang Chang, Ayan Kumar Bhunia, Jiyang Xie, Zhanyu Ma, Yi-Zhe Song, Jun Guo
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 |
|---|---|---|---|
| add jigsaw puzzle generator to progressive training (S=3) (ablation) | PMG · CUB-200-2011 (ResNet50) | combined accuracy: 88.7 -> 89.6 | Improved |
| add jigsaw puzzle generator to progressive training (S=1) (ablation) | PMG · CUB-200-2011 (ResNet50) | combined accuracy: 86.5 -> 86.9 | Improved |
| add jigsaw puzzle generator to progressive training (S=4) (ablation) | PMG · CUB-200-2011 (ResNet50) | combined accuracy: 88.5 -> 88.5 | No clear effect |
| add jigsaw puzzle generator to progressive training (S=5) (ablation) | PMG · CUB-200-2011 (ResNet50) | combined accuracy: 88.3 -> 87.7 | Hurt |
| increase number of supervised stages S from 1 to 3 (no jigsaw) (ablation) | PMG · CUB-200-2011 (ResNet50) | combined accuracy: 86.5 -> 88.7 | Improved |
| increase number of supervised stages S from 3 to 4 (no jigsaw) (ablation) | PMG · CUB-200-2011 (ResNet50) | combined accuracy: 88.7 -> 88.5 | Hurt |
| increase number of supervised stages S from 3 to 5 with jigsaw (ablation) | PMG · CUB-200-2011 (ResNet50) | combined accuracy: 89.6 -> 87.7 | Hurt |
| train progressively instead of back-propagating four outputs in one step (ablation) | PMG · CUB-200-2011 (ResNet50) | combined accuracy: 89.1 -> 89.6 | Improved |
| fuse granularities in one progressive network instead of four separate networks (ablation) | PMG · CUB-200-2011 (ResNet50) | combined accuracy: 87.7 -> 89.6 | Improved |
| raise beta from 1/3 to 2 with alpha=1 (ablation) | PMG · CUB-200-2011 (ResNet50) | combined accuracy: 88.6 -> 89.6 | Improved |
| raise beta from 2 to 3 with alpha=1 (ablation) | PMG · CUB-200-2011 (ResNet50) | combined accuracy: 89.6 -> 89.1 | Hurt |
| use combined outputs C2 instead of concat output C1 (ResNet50) | PMG · CUB-200-2011 | accuracy: 88.9 -> 89.6 | Improved |
Closest papers by meaning
- Progressive Learning of Category-Consistent Multi-Granularity Features for Fine-Grained Visual Classification (TPAMI 2021 · similarity 0.94)
- An Erudite Fine-Grained Visual Classification Model (CVPR 2023 · similarity 0.90)
- Maximum-Entropy Fine Grained Classification (NeurIPS 2018 · similarity 0.90)
- Democratizing Fine-grained Visual Recognition with Large Language Models (ICLR 2024 · similarity 0.88)
- Advancing Fine-Grained Classification by Structure and Subject Preserving Augmentation (NeurIPS 2024 · similarity 0.87)
- Novel Class Discovery for Ultra-Fine-Grained Visual Categorization (CVPR 2024 · similarity 0.86)
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.
