Research map / Label-efficient and robust learning / Semi-supervised learning
Max-Margin Invariant Features from Transformed Unlabelled Data
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 MMIF features trained on transformed unlabeled data to VGG-Face features | VGG-Face · LFW unseen-subject protocol | VR at 0.1% FAR: 0.56 to 0.71 | Helped |
| Use max pooling instead of mean pooling (ablation) | MMIF · Face recognition experiments | recognition performance | Helped |
| Constrain labeled training data to 30 randomly selected poses per subject (ablation) | MMIF-VGG · Semi-synthetic mugshot database | VR at 0.1% FAR | No clear effect |
| Use 100 instead of 500 SVM feature extractors (ablation) | MMIF · IJB-A Janus | recognition performance | No clear effect |
Closest papers by meaning
- Discriminative Invariant Kernel Features: A Bells-and-Whistles-Free Approach to Unsupervised Face Recognition and Pose Estimation (CVPR 2016 · similarity 0.88)
- Learning from Few Samples: Transformation-Invariant SVMs with Composition and Locality at Multiple Scales (NeurIPS 2022 · similarity 0.87)
- GIF: Generative Inspiration for Face Recognition at Scale (CVPR 2025 · similarity 0.85)
- Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition (NeurIPS 2024 · similarity 0.84)
- LAFS: Landmark-based Facial Self-supervised Learning for Face Recognition (CVPR 2024 · similarity 0.84)
- Decoupled Optimisation for Long-Tailed Visual Recognition (AAAI 2024 · similarity 0.84)
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.