Research map / Continual learning / Class-incremental
Class-Incremental Novel Class Discovery
Subhankar Roy, Mingxuan Liu, Zhun Zhong, Nicu Sebe, Elisa Ricci
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 feature distillation and feature replay (ablation) | FRoST · Average over three datasets (class-iNCD) | All accuracy: 9.5 -> 58.3 | Improved |
| add feature replay (with feature distillation) (ablation) | FRoST · Average over three datasets (class-iNCD) | All accuracy: 17.4 -> 58.3 | Improved |
| add feature distillation (with feature replay) (ablation) | FRoST · Average over three datasets (class-iNCD) | All accuracy: 9.9 -> 58.3 | Improved |
| add self-training with joint classifier (ablation) | FRoST · Average over three datasets (class-iNCD) | All accuracy: 51.0 -> 58.3 | Improved |
| replace LwF (pre-softmax) with feature replay and distillation (ablation) | FRoST · Average over three datasets (class-iNCD) | All accuracy: 27.0 -> 58.3 | Improved |
| add feature replay to LwF (softmax) (ablation) | LwF · Average over three datasets (class-iNCD) | All accuracy: 21.1 -> 38.4 | Improved |
| add feature replay to LwF (pre-softmax) (ablation) | LwF · Tiny-ImageNet (class-iNCD) | Old accuracy: 6.8 -> 49.9 | Improved |
| add separate novel head to joint classifier (ablation) | FRoST · Tiny-ImageNet (class-iNCD) | New accuracy: 8.4 -> 33.9 | Improved |
| add novel head to joint classifier (ablation) | FRoST · Average over three datasets (class-iNCD) | All accuracy: 58.1 -> 58.3 | No clear effect |
| add self-training to joint-only classifier (ablation) | Joint classifier · Average over three datasets (class-iNCD) | All accuracy: 52.8 -> 58.1 | Improved |
| use FRoST instead of ResTune | class-iNCD · Average over three datasets (class-iNCD) | All accuracy: 48.3 -> 54.9 | Improved |
| use FRoST instead of ResTune | class-iNCD · CIFAR-10 (class-iNCD) | New accuracy: 0.0 -> 49.5 | Improved |
Closest papers by meaning
- Adaptive Discovering and Merging for Incremental Novel Class Discovery (AAAI 2024 · similarity 0.91)
- Novel Class Discovery without Forgetting (ECCV 2022 · similarity 0.90)
- Modeling Inter-Class and Intra-Class Constraints in Novel Class Discovery (CVPR 2023 · similarity 0.89)
- Class-Incremental Learning with Cross-Space Clustering and Controlled Transfer (ECCV 2022 · similarity 0.89)
- Semantic-Guided Novel Category Discovery (AAAI 2024 · similarity 0.87)
- Joint Class-level and Instance-level Relationship Modeling for Novel Class Discovery (AAAI 2025 · similarity 0.87)
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.
