Research map / Label-efficient and robust learning / Semi-supervised learning
OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning
Mamshad Nayeem Rizve, Navid Kardan, Salman Khan, Fahad Shahbaz Khan, Mubarak Shah
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 entropy regularization (ablation) | OpenLDN · CIFAR-100 ablation (50% known, 50% labeled) | All accuracy: 33.4 -> 53.3 | Improved |
| add pairwise similarity loss with bi-level optimization (ablation) | OpenLDN · CIFAR-100 ablation (50% known, 50% labeled) | Novel accuracy: 26.6 -> 40.3 | Improved |
| add closed-world SSL training (ablation) | OpenLDN · CIFAR-100 ablation (50% known, 50% labeled) | Novel accuracy: 40.3 -> 44.9 | Improved |
| add closed-world SSL training (ablation) | OpenLDN · CIFAR-100 ablation (50% known, 50% labeled) | Known accuracy: 66.2 -> 73.9 | Improved |
| add iterative pseudo-labeling (ablation) | OpenLDN · CIFAR-100 ablation (50% known, 50% labeled) | Novel accuracy: 44.9 -> 46.8 | Improved |
| add pairwise similarity loss (ablation) | OpenLDN · CIFAR-100 ablation (50% known, 50% labeled) | Known accuracy: 66.2 -> 66.2 | No clear effect |
| replace bi-level similarity with soft cosine similarity of features (ablation) | OpenLDN · CIFAR-100 pairwise similarity estimation (50% known, 50% labeled) | Novel accuracy: 26.6 -> 10.3 | Hurt |
| replace bi-level similarity with hard cosine threshold 0.50 (ablation) | OpenLDN · CIFAR-100 pairwise similarity estimation (50% known, 50% labeled) | Novel accuracy: 26.6 -> 2.1 | Hurt |
| replace bi-level similarity with hard cosine threshold 0.95 (ablation) | OpenLDN · CIFAR-100 pairwise similarity estimation (50% known, 50% labeled) | Novel accuracy: 26.6 -> 17.3 | Hurt |
| replace bi-level similarity with nearest neighbor similarity (ablation) | OpenLDN · CIFAR-100 pairwise similarity estimation (50% known, 50% labeled) | Novel accuracy: 40.3 -> 31.7 | Hurt |
| OpenLDN-UDA instead of ORCA | OpenLDN-UDA · ImageNet-100 | Novel accuracy: 72.1 -> 68.6 | Hurt |
| OpenLDN with 10% instead of 50% labeled data | OpenLDN-MixMatch · CIFAR-100 | All accuracy: 38.6 -> 47.7 | Improved |
Later papers that compared with this method
1 later accepted paper reports OpenLDN as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- OwMatch: Conditional Self-Labeling with Consistency for Open-World Semi-Supervised Learning (NeurIPS 2024 · better on 4 of 4 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- FixMatch — FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence (NeurIPS 2020) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Towards Realistic Semi-Supervised Learning (ECCV 2022 · similarity 0.91)
- Rethinking Safe Semi-supervised Learning: Transferring the Open-set Problem to A Close-set One (ICCV 2023 · similarity 0.90)
- OwMatch: Conditional Self-Labeling with Consistency for Open-World Semi-Supervised Learning (NeurIPS 2024 · similarity 0.90)
- Open-World Semi-Supervised Learning (ICLR 2022 · similarity 0.90)
- Robust Semi-Supervised Learning when Not All Classes have Labels (NeurIPS 2022 · similarity 0.89)
- Targeted Representation Alignment for Open-World Semi-Supervised Learning (CVPR 2024 · similarity 0.89)
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.
