Research map / Continual learning / Class-incremental
Learning Without Memorizing
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 attention distillation loss to classification and distillation losses | LwF-MC · iILSVRC-small | overall accuracy | Helped |
| Add attention distillation loss to classification and distillation losses | LwF-MC · iCIFAR-100 (incremental batches of 10, 20, and 50 classes) | overall accuracy | Helped |
| Add attention distillation loss to classification and distillation losses | Finetuning · Caltech-101 | top-1 accuracy | Helped |
| Add attention distillation loss to classification and distillation losses | Finetuning · CUBS-200-2011 | top-1 accuracy | Helped |
| Add distillation loss to classification and attention distillation losses (ablation) | Classification + attention distillation · iILSVRC-small | top-5 accuracy: 84.95 -> 99.55; 55.82 -> 99.18; 43.46 -> 98.72 | Helped |
| Add distillation loss to classification loss (ablation) | Finetuning · Incremental object classification | overall accuracy | Helped |
| Add attention distillation loss to classification and distillation losses (ablation) | LwF-MC · Incremental object classification | overall accuracy | Helped |
| Remove distillation and attention distillation losses (ablation) | LwM (classification-only finetuning) · Incremental object classification | overall accuracy | Hurt |
| Replace L1 attention-map distance with L2 distance (ablation) | LwM · Held-out data | performance | Hurt |
Closest papers by meaning
- eTag: Class-Incremental Learning via Embedding Distillation and Task-Oriented Generation (AAAI 2024 · similarity 0.88)
- Long-Tail Class Incremental Learning via Independent Sub-prototype Construction (CVPR 2024 · similarity 0.87)
- Gradient Reweighting: Towards Imbalanced Class-Incremental Learning (CVPR 2024 · similarity 0.86)
- Class Incremental Learning with Multi-Teacher Distillation (CVPR 2024 · similarity 0.86)
- Multi-layer Rehearsal Feature Augmentation for Class-Incremental Learning (ICML 2024 · similarity 0.86)
- Compress to One Point: Neural Collapse for Pre-Trained Model-Based Class-Incremental Learning (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.