Research map / Continual learning / Online and replay-based
Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inference
Read the paperCheck 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 |
|---|---|---|---|
| Use CLIB instead of Baseline-ER | Online continual learning · CIFAR10 i-Blurry-50-10 | A_AUC: 57.46$\pm$2.25 -> 70.26$\pm$1.28 | Helped |
| Use CLIB instead of Baseline-ER | Online continual learning · CIFAR100 i-Blurry-50-10 | A_AUC: 35.61$\pm$2.08 -> 46.67$\pm$0.79 | Helped |
| Use CLIB instead of Baseline-ER | Online continual learning · TinyImageNet i-Blurry-50-10 | A_AUC: 22.45$\pm$1.15 -> 23.87$\pm$0.68 | Helped |
| Use CLIB instead of Baseline-ER | Online continual learning · ImageNet i-Blurry-50-10 | A_AUC: 25.16 -> 28.16 | Helped |
| Add sample-wise importance memory management (ablation) | CLIB · CIFAR10 i-Blurry-50-10 | A_AUC: 53.75$\pm$2.11 -> 70.26$\pm$1.28 | Helped |
| Add sample-wise importance memory management (ablation) | CLIB · CIFAR100 i-Blurry-50-10 | A_AUC: 36.59$\pm$1.22 -> 46.67$\pm$0.79 | Helped |
| Train only from memory rather than using ER stream-plus-memory batches (ablation) | CLIB · CIFAR10 i-Blurry-50-10 | A_AUC: 67.06$\pm$1.51 -> 70.26$\pm$1.28 | Helped |
| Train only from memory rather than using ER stream-plus-memory batches (ablation) | CLIB · CIFAR100 i-Blurry-50-10 | A_AUC: 44.63$\pm$0.22 -> 46.67$\pm$0.79 | Helped |
| Use adaptive LR scheduling instead of exponential-with-reset scheduling (ablation) | CLIB · CIFAR10 i-Blurry-50-10 | A_AUC: 69.70$\pm$1.34 -> 70.26$\pm$1.28 | Helped |
| Use adaptive LR scheduling instead of exponential-with-reset scheduling (ablation) | CLIB · CIFAR100 i-Blurry-50-10 | A_AUC: 45.01$\pm$0.22 -> 46.67$\pm$0.79 | Helped |
Closest papers by meaning
- Budgeted Online Continual Learning by Adaptive Layer Freezing and Frequency-based Sampling (ICLR 2025 · similarity 0.89)
- Re-evaluating Continual Learning with Few-Shot Adaptation (NeurIPS 2026 · similarity 0.88)
- Enhancing Online Continual Learning with Plug-and-Play State Space Model and Class-Conditional Mixture of Discretization (CVPR 2025 · similarity 0.88)
- Online Task-Free Continual Learning via Dynamic Expansionable Memory Distribution (CVPR 2025 · similarity 0.88)
- Non-exemplar Online Class-Incremental Continual Learning via Dual-Prototype Self-Augment and Refinement (AAAI 2024 · similarity 0.88)
- Adaptive Retention & Correction: Test-Time Training for Continual Learning (ICLR 2025 · similarity 0.88)
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.