Research map / Label-efficient and robust learning / Semi-supervised learning
Automatically Discovering and Learning New Visual Categories with Ranking Statistics
Kai Han, Sylvestre-Alvise Rebuffi, Sebastien Ehrhardt, Andrea Vedaldi, Andrew Zisserman
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 rank-statistics pairwise pseudo-labeling with BCE training (ablation) | Novel category discovery · CIFAR-10 | ACC: 26.2 -> 90.4 | Improved |
| Add consistency constraints (ablation) | Novel category discovery · CIFAR-10 | ACC: 82.6 -> 90.4 | Improved |
| Add cross-entropy training on labelled data (ablation) | Novel category discovery · CIFAR-10 | ACC: 84.7 -> 90.4 | Improved |
| Add self-supervised pretraining (ablation) | Novel category discovery · CIFAR-10 | ACC: 89.4 -> 90.4 | Improved |
| Add incremental learning of discovered classes (ablation) | Ours full · CIFAR-10 | ACC: 90.4 -> 91.7 | Improved |
| Add incremental learning of discovered classes (ablation) | Ours full · CIFAR-100 | ACC: 73.2 -> 75.2 | Improved |
| Add incremental learning of discovered classes (ablation) | Ours full · SVHN | ACC: 95.0 -> 95.2 | Improved |
| Use the full rank-based joint method instead of DTC with self-supervised initialization | Novel category discovery · CIFAR-10, CIFAR-100, and SVHN | ACC: 88.7$\pm$0.3\% -> 90.4$\pm$0.5\%; 67.3$\pm$1.2\% -> 73.2$\pm$2.1\%; 75.7$\pm$0.4\% -> 95.0$\pm$0.2\% | Improved |
| Use the full method instead of DTC | Novel category discovery · OmniGlot | ACC: 89.0\% -> 89.1\% | Improved |
| Use the full method instead of DTC | Novel category discovery · ImageNet | ACC: 78.3\% -> 82.5\% | Improved |
| Replace self-supervised pretraining with metric-learning pretraining | Novel category discovery · OmniGlot and ImageNet | ACC | No clear effect |
Closest papers by meaning
- AutoNovel: Automatically Discovering and Learning Novel Visual Categories (TPAMI 2021 · similarity 0.94)
- Labeled Data Selection for Category Discovery (ECCV 2024 · similarity 0.91)
- Automatically Discovering Novel Visual Categories With Adaptive Prototype Learning (TPAMI 2023 · similarity 0.91)
- Semantic-Guided Novel Category Discovery (AAAI 2024 · similarity 0.89)
- Image Clustering via the Principle of Rate Reduction in the Age of Pretrained Models (ICLR 2024 · similarity 0.87)
- Prior-Constrained Association Learning for Fine-Grained Generalized Category Discovery (AAAI 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.
