Research map / Vision-language and multimodal / Human and embodied modeling
Dynamic Position-aware Network for Fine-grained Image Recognition
Shijie Wang, Haojie Li, Zhihui Wang, Wanli Ouyang
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 discriminative patch sampling to the BL baseline (ablation) | BL on CUB-200-2011 · CUB-200-2011 | accuracy: +2.6% | Improved |
| Add PEM and PRM to the sampled baseline (ablation) | BL + Sample on CUB-200-2011 · CUB-200-2011 | accuracy: 87.1% -> 88.4% | Improved |
| Add PAM to the PEM + PRM variant (ablation) | BL + Sample + PEM + PRM on CUB-200-2011 · CUB-200-2011 | accuracy: 88.4% -> 89.3% | Improved |
| Use graph depth 2 instead of depth 1 (ablation) | DP-Net on CUB-200-2011 · CUB-200-2011 | accuracy: 88.2% -> 88.7% | Improved |
| Use graph depth 3 instead of depth 2 (ablation) | DP-Net on CUB-200-2011 · CUB-200-2011 | accuracy: 88.7% -> 89.3% | Improved |
| Increase graph depth from 3 to 4 (ablation) | DP-Net on CUB-200-2011 · CUB-200-2011 | accuracy: 89.3% -> 89.1% | Hurt |
| Increase graph depth from 3 to 5 (ablation) | DP-Net on CUB-200-2011 · CUB-200-2011 | accuracy: 89.3% -> 88.6% | Hurt |
| Add DP-Net position-aware learning to the original feature branch (ablation) | Original Feature Branch on CUB-200-2011 · CUB-200-2011 | accuracy: 87.1% -> 88.2% | Improved |
| Use the position-aware feature branch instead of the original feature branch (ablation) | DP-Net on CUB-200-2011 · CUB-200-2011 | accuracy: 88.2% -> 88.5% | Improved |
| Combine the original and position-aware feature branches (ablation) | DP-Net on CUB-200-2011 · CUB-200-2011 | accuracy: 88.2% -> 89.3% | Improved |
| Use DP-Net instead of the strongest listed baseline | Fine-grained recognition · CUB-200-2011 | accuracy: 88.5% -> 89.3% | Improved |
| Use DP-Net instead of the strongest listed baseline | Fine-grained recognition · Stanford Cars-196 | accuracy: 94.7% -> 94.8% | Improved |
Closest papers by meaning
- Fine-Grained Segmentation Networks: Self-Supervised Segmentation for Improved Long-Term Visual Localization (ICCV 2019 · similarity 0.86)
- Spatial-Aware Token for Weakly Supervised Object Localization (ICCV 2023 · similarity 0.86)
- Sequential Visual Place Recognition: Exploiting Trajectory Priors for Robust Localization (ECCV 2026 · similarity 0.85)
- Recognize Any Regions (NeurIPS 2024 · similarity 0.84)
- Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition (AAAI 2025 · similarity 0.84)
- Optimal Transport Aggregation for Visual Place Recognition (CVPR 2024 · similarity 0.83)
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.
