Research map / Vision-language and multimodal / Human and embodied modeling
Fine-Grained Image Analysis With Deep Learning: A Survey
Xiu-Shen Wei, Yi-Zhe Song, Oisin Mac Aodha, Jianxin Wu, Yuxin Peng, Jinhui Tang, Jian Yang, Serge Belongie
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 |
|---|---|---|---|
| increase input resolution from 224x224 to 280x280 (ablation) | vanilla ResNet-50 · CUB200-2011 | accuracy: 81.6% -> 83.3% | Improved |
| increase input resolution from 280x280 to 336x336 (ablation) | vanilla ResNet-50 · CUB200-2011 | accuracy: 83.3% -> 85.0% | Improved |
| increase input resolution from 336x336 to 392x392 (ablation) | vanilla ResNet-50 · CUB200-2011 | accuracy: 85.0% -> 85.6% | Improved |
| add bounding-box annotation for training | BGL (VGG-16, 224x224) · CUB200-2011 | accuracy: 75.9% -> 80.4% | Improved |
| add maximum-entropy loss on bilinear backbone vs plain VGG-16 | MaxEnt · CUB200-2011 | accuracy: 77.0% -> 85.3% | Improved |
| replace VGG-16 with DenseNet-161 backbone | API-Net · CUB200-2011 | accuracy: 87.7% -> 90.0% | Improved |
| use ResNet-50 instead of VGG-16 backbone for PMA language-guided method | PMA · CUB200-2011 | accuracy: 88.2% -> 88.7% | Improved |
Closest papers by meaning
- The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition (ECCV 2016 · similarity 0.90)
- Webly Supervised Fine-Grained Recognition: Benchmark Datasets and an Approach (ICCV 2021 · similarity 0.89)
- Fine-Grained Recognition: Accounting for Subtle Differences between Similar Classes (AAAI 2020 · similarity 0.88)
- Fine-grained Classes and How to Find Them (ICML 2024 · similarity 0.87)
- Few-Shot Fine-Grained Image Classification with Progressively Feature Refinement and Continuous Relationship Modeling (AAAI 2025 · similarity 0.87)
- Cross-Layer and Cross-Sample Feature Optimization Network for Few-Shot Fine-Grained Image Classification (AAAI 2024 · similarity 0.87)
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.
