Research map / Continual learning / Online and replay-based
Achieving a Better Stability-Plasticity Trade-Off via Auxiliary Networks in Continual Learning
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 |
|---|---|---|---|
| Add an auxiliary-network regularizer to LwF | LwF · CIFAR-100/10 (TIL) | averaged accuracy (%): 78.87_{\pm0.69} -> 79.42_{\pm0.57} | Helped |
| Add an auxiliary-network regularizer to LwF | LwF · CIFAR-100/20 (TIL) | averaged accuracy (%): 76.96_{\pm0.83} -> 79.99_{\pm0.59} | Helped |
| Add an auxiliary-network regularizer to LwF | LwF · Tiny ImageNet-200/10 (TIL) | averaged accuracy (%): 59.04_{\pm0.62} -> 60.96_{\pm0.76} | Helped |
| Add an auxiliary-network regularizer to LwF | LwF · Tiny ImageNet-200/20 (TIL) | averaged accuracy (%): 62.09_{\pm0.59} -> 63.79_{\pm0.41} | Helped |
| Add an auxiliary-network regularizer to PODNet | PODNet · CIFAR-100/6 (CIL) | averaged incremental accuracy (%): 61.80_{\pm0.77} -> 63.15_{\pm0.62} | Helped |
| Add an auxiliary-network regularizer to PODNet | PODNet · CIFAR-100/11 (CIL) | averaged incremental accuracy (%): 59.22_{\pm0.93} -> 60.44_{\pm0.67} | Helped |
| Add an auxiliary-network regularizer to BiC | BiC · Tiny ImageNet-200/11 (CIL) | averaged incremental accuracy (%): 40.56_{\pm0.44} -> 42.61_{\pm0.65} | Helped |
| Add an auxiliary-network regularizer to BiC | BiC · Tiny ImageNet-200/21 (CIL) | averaged incremental accuracy (%): 39.21_{\pm0.69} -> 40.56_{\pm0.51} | Helped |
Closest papers by meaning
- Rethinking the Stability-Plasticity Trade-off in Continual Learning from an Architectural Perspective (ICML 2025 · similarity 0.93)
- Improving Continual Learning Performance and Efficiency with Auxiliary Classifiers (ICML 2025 · similarity 0.90)
- STAR: Stability-Inducing Weight Perturbation for Continual Learning (ICLR 2025 · similarity 0.89)
- Train with Perturbation, Infer after Merging: A Two-Stage Framework for Continual Learning (NeurIPS 2025 · similarity 0.89)
- Pareto Continual Learning: Preference-Conditioned Learning and Adaption for Dynamic Stability-Plasticity Trade-off (AAAI 2025 · similarity 0.89)
- Recall-Oriented Continual Learning with Generative Adversarial Meta-Model (AAAI 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.