Research map / Label-efficient and robust learning / Recognition and long-tail
Logo-2K+: A Large-Scale Logo Dataset for Scalable Logo Classification
Jing Wang, Weiqing Min, Sujuan Hou, Shengnan Ma, Yuanjie Zheng, Haishuai Wang, Shuqiang Jiang
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 DRNA-Net instead of NTS-Net | Logo classification with ResNet-50 · Logo-2K+ test | Top-1 accuracy: 69.41 -> 71.12 | Improved |
| Use DRNA-Net instead of NTS-Net | Logo classification with ResNet-50 · Logo-2K+ test | Top-5 accuracy: 91.95 -> 92.33 | Improved |
| Use DRNA-Net instead of NTS-Net | Logo classification with ResNet-50 · BelgaLogos test | Top-1 accuracy: 93.33 -> 94.44 | Improved |
| Use DRNA-Net instead of NTS-Net | Logo classification with ResNet-50 · BelgaLogos test | Top-5 accuracy: 96.15 -> 97.11 | Improved |
| Use DRNA-Net instead of NTS-Net | Logo classification with ResNet-50 · FlickrLogos-32 test | Top-1 accuracy: 94.14 -> 95.33 | Improved |
| Use DRNA-Net instead of NTS-Net | Logo classification with ResNet-50 · FlickrLogos-32 test | Top-5 accuracy: 96.29 -> 97.17 | Improved |
| Use DRNA-Net instead of NTS-Net | Logo classification with ResNet-50 · WebLogo-2M test | Top-1 accuracy: 63.67 -> 64.82 | Improved |
| Use DRNA-Net instead of NTS-Net | Logo classification with ResNet-50 · WebLogo-2M test | Top-5 accuracy: 84.31 -> 86.12 | Improved |
| Use a ResNet-152 rather than ResNet-50 backbone in DRNA-Net | DRNA-Net · Logo-2K+ test | Top-1 accuracy: 71.12 -> 72.09 | Improved |
| Use a ResNet-152 rather than ResNet-50 backbone in DRNA-Net | DRNA-Net · BelgaLogos test | Top-1 accuracy: 94.44 -> 95.82 | Improved |
| Use a ResNet-152 rather than ResNet-50 backbone in DRNA-Net | DRNA-Net · FlickrLogos-32 test | Top-1 accuracy: 95.33 -> 96.63 | Improved |
Closest papers by meaning
- Large-Scale Logo Detection (TPAMI 2025 · similarity 0.90)
- Doomed to Re-Annotate, Forever: The ImageNet Story (NeurIPS 2026 · similarity 0.80)
- SELECT: A Large-Scale Benchmark of Data Curation Strategies for Image Classification (NeurIPS 2024 · similarity 0.80)
- Logarithmic Lenses: Exploring Log RGB Data for Image Classification (CVPR 2024 · similarity 0.80)
- Physical Marker: Revealing Invisible Hyperlinks Hidden in Printed Trademarks (AAAI 2025 · similarity 0.79)
- ARNet: Self-Supervised FG-SBIR with Unified Sample Feature Alignment and Multi-Scale Token Recycling (AAAI 2025 · similarity 0.79)
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.
