AI Paper Atlas

Research map / Continual learning / Online and replay-based

Mitigating Forgetting in Online Continual Learning with Neuron Calibration

Haiyan Yin, Peng Yang, Ping Li

NeurIPS 2021 · Continual learning › Online and replay-based · approach: Plug-and-play online training enhancements · 16 citations (OpenAlex)

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 changedWhereMeasuredEffect
use NCCL neuron calibration with EWC and interleaved optimization instead of CTNonline continual learning · Split CIFARACC: 68.62 -> 74.39Improved
NCCL instead of CTNonline continual learning · CORe50FM: 5.71 -> 2.22Improved
NCCL instead of CTNonline continual learning · Split miniImageNetACC: 65.25 -> 69.49Improved
NCCL instead of Independent per-task modelsonline continual learning · pMNISTACC: 83.50 -> 83.47No clear effect
train calibrator with memory rehearsal and update base parameters (NCCL) instead of CCLL with frozen base (ablation)calibration-based continual learning · Split CIFARACC: 64.77 -> 74.39Improved
update base parameters in addition to calibrator in CCLL (ablation)CCLL · Split miniImageNetACC: 60.56 -> 68.80Improved
increase replay memory per task from 50 to 250NCCL, CTN, MIR, GEM · Split CIFAR/miniImageNetACCImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy