Research map / Label-efficient and robust learning / Recognition and long-tail
Cross-X Learning for Fine-Grained Visual Categorization
Wei Luo, Xitong Yang, Xianjie Mo, Yuheng Lu, Larry S. Davis, Jun Li, Jian Yang, Ser-Nam Lim
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 GMP instead of GAP on mid-level features (with CL, no merged maps) (ablation) | Cross-X (SENet-50) · NABirds | top-1 accuracy: 76.3 -> 81.7 | Improved |
| use GMP instead of GAP on mid-level features (with CL, no merged maps) (ablation) | Cross-X (SENet-50) · Stanford Cars | top-1 accuracy: 90.4 -> 93.0 | Improved |
| use GMP instead of GAP on mid-level features (with CL, no merged maps) (ablation) | Cross-X (SENet-50) · Stanford Dogs | top-1 accuracy: 87.3 -> 83.0 | Hurt |
| use GAP instead of GMP on mid-level features (with merged maps, no CL) (ablation) | Cross-X (SENet-50) · Stanford Cars | top-1 accuracy: 91.9 -> 93.8 | Improved |
| use GAP instead of GMP on mid-level features (with merged maps, no CL) (ablation) | Cross-X (SENet-50) · CUB-Birds | top-1 accuracy: 84.2 -> 84.7 | No clear effect |
| add C3S regularizer to OSME network (ablation) | OSME on SENet-50 · five FGVC benchmarks | top-1 accuracy | Improved |
| add CL regularizer to the C3S+GMP network (ablation) | OSME + C3S + GMP · five FGVC benchmarks | top-1 accuracy | Improved |
| combine mid- and high-level features without a CL constraint (ablation) | OSME + C3S · five FGVC benchmarks | top-1 accuracy | Hurt |
| add merged (FPN) feature maps (ablation) | Cross-X (SENet-50) · five FGVC benchmarks | top-1 accuracy | Improved |
| add CL when merged feature maps are used (ablation) | Cross-X (SENet-50) · five FGVC benchmarks | top-1 accuracy | Improved |
| replace metric-learning loss of MAMC-CNN with C3S and CL (Cross-X vs MAMC-CNN) | Cross-X (ResNet) · Stanford Cars | top-1 accuracy: 93.0 -> 94.6 | Improved |
| Cross-X ResNet-50 versus MaxEnt-CNN with DenseNet-161 | Cross-X (ResNet) · NABirds | top-1 accuracy: 83.0 -> 86.2 | Improved |
Closest papers by meaning
- Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification (CVPR 2022 · similarity 0.87)
- Fine-Grained Image Classification via Combining Vision and Language (CVPR 2017 · similarity 0.86)
- Weakly Supervised Learning of Part Selection Model with Spatial Constraints for Fine-Grained Image Classification (AAAI 2017 · similarity 0.86)
- Webly-Supervised Fine-Grained Visual Categorization via Deep Domain Adaptation (TPAMI 2016 · similarity 0.86)
- Democratizing Fine-grained Visual Recognition with Large Language Models (ICLR 2024 · similarity 0.85)
- Cross-Layer and Cross-Sample Feature Optimization Network for Few-Shot Fine-Grained Image Classification (AAAI 2024 · similarity 0.85)
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.
