Research map / Label-efficient and robust learning / Recognition and long-tail
Weakly Supervised Fine-Grained Image Classification via Guassian Mixture Model Oriented Discriminative Learning
Zhihui Wang, Shijie Wang, Shuhui Yang, Haojie Li, Jianjun Li, Zezhou Li
Check 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 score-based default-patch sampling to the ResNet-50 baseline. (ablation) | BL · CUB-200-2011 | accuracy: 84.5% -> 86.2% | Improved |
| Add DF-GMM to score-based patch sampling. (ablation) | BL + Sample · CUB-200-2011 | accuracy: 86.2% -> 88.8% | Improved |
| Add score-based sampling to the baseline. (ablation) | BL · CUB-200-2011 | speed: n/a -> 50 fps | Improved |
| Add DF-GMM to score-based patch sampling. (ablation) | BL + Sample · CUB-200-2011 | speed: 50 fps -> 41 fps | Hurt |
| Use global average pooling instead of random initialization for low-rank bases. (ablation) | DF-GMM · CUB-200-2011 | accuracy: 87.1% -> 88.8% | Improved |
| Use global average pooling instead of global max pooling for low-rank base initialization. (ablation) | DF-GMM · CUB-200-2011 | accuracy: 87.9% -> 88.8% | Improved |
| Increase the GMM iteration count from 1 to 3. (ablation) | DF-GMM · CUB-200-2011 | accuracy: 86.9% -> 88.8% | Improved |
| Increase the GMM iteration count from 2 to 3. (ablation) | DF-GMM · CUB-200-2011 | accuracy: 87.5% -> 88.8% | Improved |
| Increase the GMM iteration count from 3 to 4. (ablation) | DF-GMM · CUB-200-2011 | accuracy: 88.8% -> 88.4% | Hurt |
| Increase the GMM iteration count from 3 to 5. (ablation) | DF-GMM · CUB-200-2011 | accuracy: 88.8% -> 88.1% | Hurt |
| Increase the number of selected discriminative patches from 2 to 4. (ablation) | DF-GMM · CUB-200-2011 | accuracy: 88.10% -> 88.80% | Improved |
| Increase the number of selected discriminative patches from 2 to 4. (ablation) | DF-GMM · CUB-200-2011 | speed: 43.00 -> 41.00 | Hurt |
Closest papers by meaning
- Graph-Propagation Based Correlation Learning for Weakly Supervised Fine-Grained Image Classification (AAAI 2020 · similarity 0.88)
- Learning a Discriminative Filter Bank Within a CNN for Fine-Grained Recognition (CVPR 2018 · similarity 0.87)
- Look Closer to See Better: Recurrent Attention Convolutional Neural Network for Fine-Grained Image Recognition (CVPR 2017 · similarity 0.87)
- Learning Multi-Attention Convolutional Neural Network for Fine-Grained Image Recognition (ICCV 2017 · similarity 0.86)
- Interpretable and Accurate Fine-grained Recognition via Region Grouping (CVPR 2020 · similarity 0.86)
- Learning Separable Fine-Grained Representation via Dendrogram Construction from Coarse Labels for Fine-grained Visual Recognition (ICCV 2025 · similarity 0.86)
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.
