Research map / Detection and segmentation / CNN features
Destruction and Construction Learning for Fine-Grained Image Recognition
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 |
|---|---|---|---|
| Use DCL instead of the ResNet-50 baseline | ResNet-50 · CUB-200-2011 | accuracy: 85.5 -> 87.8 | Helped |
| Use DCL instead of the ResNet-50 baseline | ResNet-50 · Stanford Cars | accuracy: 92.7 -> 94.5 | Helped |
| Use DCL instead of the ResNet-50 baseline | ResNet-50 · FGVC-Aircraft | accuracy: 90.3 -> 92.2 | Helped |
| Add RCM classification training to the baseline (ablation) | ResNet-50 · CUB-200-2011 | accuracy: 85.5 -> 86.2 | Helped |
| Add RCM classification training to the baseline (ablation) | ResNet-50 · Stanford Cars | accuracy: 92.7 -> 93.4 | Helped |
| Add RCM classification training to the baseline (ablation) | ResNet-50 · FGVC-Aircraft | accuracy: 90.3 -> 89.9 | Hurt |
| Add adversarial loss to RCM classification training (ablation) | ResNet-50 · CUB-200-2011 | accuracy: 86.2 -> 87.2 | Helped |
| Add adversarial loss to RCM classification training (ablation) | ResNet-50 · Stanford Cars | accuracy: 93.4 -> 94.4 | Helped |
| Add adversarial loss to RCM classification training (ablation) | ResNet-50 · FGVC-Aircraft | accuracy: 89.9 -> 91.6 | Helped |
| Add region construction loss to classification training (ablation) | ResNet-50 · CUB-200-2011 | accuracy: 85.5 -> 86.7 | Helped |
| Add region construction loss to classification training (ablation) | ResNet-50 · Stanford Cars | accuracy: 92.7 -> 94.1 | Helped |
| Add region construction loss to classification training (ablation) | ResNet-50 · FGVC-Aircraft | accuracy: 90.3 -> 90.7 | Helped |
Closest papers by meaning
- Fine-Grained Recognition: Accounting for Subtle Differences between Similar Classes (AAAI 2020 · similarity 0.86)
- Interpretable and Accurate Fine-grained Recognition via Region Grouping (CVPR 2020 · similarity 0.85)
- Fine-Grained Image Classification via Combining Vision and Language (CVPR 2017 · similarity 0.85)
- Fine-Grained Recognition as HSnet Search for Informative Image Parts (CVPR 2017 · similarity 0.84)
- Twofold Debiasing Enhances Fine-Grained Learning with Coarse Labels (AAAI 2025 · similarity 0.82)
- Democratizing Fine-grained Visual Recognition with Large Language Models (ICLR 2024 · similarity 0.82)
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.