Research map / Continual learning / Class-incremental
Self-Sustaining Representation Expansion for Non-Exemplar Class-Incremental Learning
Check 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 dynamic structure reorganization (DSR) (ablation) | Self-Sustaining Representation Expansion · CIFAR-100, 5 phases | average incremental accuracy (%): 61.11 -> 64.86 | Helped |
| Add dynamic structure reorganization (DSR) (ablation) | Self-Sustaining Representation Expansion · CIFAR-100, 10 phases | average incremental accuracy (%): 57.08 -> 63.25 | Helped |
| Add dynamic structure reorganization (DSR) (ablation) | Self-Sustaining Representation Expansion · CIFAR-100, 20 phases | average incremental accuracy (%): 51.04 -> 54.09 | Helped |
| Add main-branch distillation (MBD) (ablation) | Self-Sustaining Representation Expansion · CIFAR-100, 5 phases | average incremental accuracy (%): 61.11 -> 62.70 | Helped |
| Add main-branch distillation (MBD) (ablation) | Self-Sustaining Representation Expansion · CIFAR-100, 10 phases | average incremental accuracy (%): 57.08 -> 62.60 | Helped |
| Add main-branch distillation (MBD) (ablation) | Self-Sustaining Representation Expansion · CIFAR-100, 20 phases | average incremental accuracy (%): 51.04 -> 58.57 | Helped |
| Add prototype selection mechanism (PSM) to DSR and MBD (ablation) | Self-Sustaining Representation Expansion · CIFAR-100, 5 phases | average incremental accuracy (%): 65.10 -> 65.88 | Helped |
| Add prototype selection mechanism (PSM) to DSR and MBD (ablation) | Self-Sustaining Representation Expansion · CIFAR-100, 10 phases | average incremental accuracy (%): 63.87 -> 64.69 | Helped |
| Add prototype selection mechanism (PSM) to DSR and MBD (ablation) | Self-Sustaining Representation Expansion · CIFAR-100, 20 phases | average incremental accuracy (%): 60.60 -> 61.61 | Helped |
| Use a 1×1 convolution adapter instead of a 3×3 convolution adapter (ablation) | Self-Sustaining Representation Expansion · CIFAR-100, 5 phases | average incremental accuracy (%): 64.28 -> 65.87 | Helped |
| Use a 1×1 convolution adapter instead of a 3×3 convolution adapter (ablation) | Self-Sustaining Representation Expansion · CIFAR-100, 10 phases | average incremental accuracy (%): 63.47 -> 65.12 | Helped |
| Use a 1×1 convolution adapter instead of a 3×3 convolution adapter (ablation) | Self-Sustaining Representation Expansion · CIFAR-100, 20 phases | average incremental accuracy (%): 60.81 -> 61.60 | Helped |
Closest papers by meaning
- Prospective Representation Learning for Non-Exemplar Class-Incremental Learning (NeurIPS 2024 · similarity 0.89)
- Non-exemplar Online Class-Incremental Continual Learning via Dual-Prototype Self-Augment and Refinement (AAAI 2024 · similarity 0.88)
- Adaptive Discovering and Merging for Incremental Novel Class Discovery (AAAI 2024 · similarity 0.87)
- Long-Tail Class Incremental Learning via Independent Sub-prototype Construction (CVPR 2024 · similarity 0.87)
- Tripartite Weight-Space Ensemble for Few-Shot Class-Incremental Learning (CVPR 2025 · similarity 0.87)
- Reducing Class-wise Confusion for Incremental Learning with Disentangled Manifolds (CVPR 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.