Research map / Label-efficient and robust learning / Recognition and long-tail
Simultaneous Feature and Sample Reduction for Image-Set Classification
Man Zhang, Ran He, Dong Cao, Zhenan Sun, Tieniu Tan
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 |
|---|---|---|---|
| apply low-rank binarization of the probe set (Eq. 16) instead of independent sign quantization (ablation) | SFSR · Honda compressed rate | compressed rate | Improved |
| initialize B0 with CCA+ITQ instead of PCA+ITQ (ablation) | SFSR · YouTube Celebrities | recognition rate | No clear effect |
| use SFSR instead of the strongest floating-feature image-set method (MSSRC) | YouTube Celebrities · YouTube Celebrities | accuracy (%): 80.75% -> 85.74% | Improved |
| use SFSR instead of SDH hashing | Honda · Honda | compressed rate | Hurt |
Closest papers by meaning
- Empowering Simple Binary Classifiers for Image Set Based Face Recognition (IJCV 2017 · similarity 0.88)
- FaceCoresetNet: Differentiable Coresets for Face Set Recognition (AAAI 2024 · similarity 0.85)
- Permutation-Invariant Feature Restructuring for Correlation-Aware Image Set-Based Recognition (ICCV 2019 · similarity 0.85)
- Pairwise Linear Regression Classification for Image Set Retrieval (CVPR 2016 · similarity 0.84)
- Open-Set Recognition: A Good Closed-Set Classifier is All You Need (ICLR 2022 · similarity 0.84)
- RepFace: Refining Closed-Set Noise with Progressive Label Correction for Face Recognition (AAAI 2025 · similarity 0.81)
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.
