Research map / Label-efficient and robust learning / Recognition and long-tail
Selective Sparse Sampling for Fine-Grained Image Recognition
Yao Ding, Yanzhao Zhou, Yi Zhu, Qixiang Ye, Jianbin Jiao
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 branch to original-only network (ablation) | S3N O · CUB-200-2011 | total top-1 accuracy (%): 86.0 -> 87.6 | Improved |
| add complementary branch to original-only network (ablation) | S3N O · CUB-200-2011 | total top-1 accuracy (%): 86.0 -> 87.3 | Improved |
| add complementary branch to O+D (ablation) | S3N O+D · CUB-200-2011 | total top-1 accuracy (%): 87.6 -> 88.5 | Improved |
| add discriminative branch to O+C (ablation) | S3N O+C · CUB-200-2011 | total top-1 accuracy (%): 87.3 -> 88.5 | Improved |
| add original branch to D+C (ablation) | S3N D+C · CUB-200-2011 | total top-1 accuracy (%): 87.5 -> 88.5 | Improved |
| add discriminative branch (ablation) | S3N O+C · CUB-200-2011 | top-1 localization accuracy (%): 56.6 -> 65.2 | Improved |
| add complementary branch (ablation) | S3N O+D · CUB-200-2011 | top-1 localization accuracy (%): 59.2 -> 65.2 | Improved |
| use sparse attention instead of class-agnostic saliency attention (ablation) | S3N · CUB-200-2011 | top-1 accuracy (%): 85.9 -> 88.5 | Improved |
| use sparse attention instead of dense class response attention (ablation) | S3N · CUB-200-2011 | top-1 accuracy (%): 87.8 -> 88.5 | Improved |
| probabilistic partition instead of giving all attention to both branches (ablation) | S3N · CUB-200-2011 | top-1 accuracy (%): 87.7 -> 88.5 | Improved |
| probabilistic partition instead of random partition (ablation) | S3N · CUB-200-2011 | top-1 accuracy (%): 87.9 -> 88.5 | Improved |
| S3N versus ResNet-50 baseline (FT ResNet) | ResNet-50 · CUB-200-2011 | top-1 accuracy (%): 86.0 -> 88.5 | Improved |
Closest papers by meaning
- Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-Grained Image Recognition (CVPR 2019 · similarity 0.89)
- Picking Deep Filter Responses for Fine-Grained Image Recognition (CVPR 2016 · similarity 0.87)
- Learning Separable Fine-Grained Representation via Dendrogram Construction from Coarse Labels for Fine-grained Visual Recognition (ICCV 2025 · similarity 0.87)
- Improving Fine-Grained Visual Recognition in Low Data Regimes via Self-Boosting Attention Mechanism (ECCV 2022 · similarity 0.87)
- SparseFormer: Sparse Visual Recognition via Limited Latent Tokens (ICLR 2024 · similarity 0.85)
- SELECT: A Large-Scale Benchmark of Data Curation Strategies for Image Classification (NeurIPS 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.
