AI Paper Atlas

Research map / Continual learning / Online and replay-based

TriRE: A Multi-Mechanism Learning Paradigm for Continual Knowledge Retention and Promotion

Preetha Vijayan, Prashant Shivaram Bhat, Bahram Zonooz, Elahe Arani

NeurIPS 2023 · Continual learning › Online and replay-based · approach: Theoretical analysis of forgetting · 0 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 TriRE instead of the strongest rehearsal baselineSeq-TinyImageNet Class-IL · Seq-TinyImageNet Class-ILaverage top-1 accuracy (%): 20.14 vs 17.68Improved
Use TriRE instead of the strongest rehearsal baselineSeq-TinyImageNet Task-IL · Seq-TinyImageNet Task-ILaverage top-1 accuracy (%): 55.95 vs 52.60Improved
Use TriRE instead of CLS-ERSeq-CIFAR10 Task-IL · Seq-CIFAR10 Task-ILaverage top-1 accuracy (%): 93.59 vs 92.45Hurt
Use TriRE instead of CLS-ERSeq-CIFAR100 Task-IL · Seq-CIFAR100 Task-ILaverage top-1 accuracy (%): 72.01 vs 71.66Hurt
Add Revise to Retain + Rewind (ablation)TriRE · Seq-CIFAR100 Task-ILaverage top-1 accuracy (%): 72.09 -> 71.66Hurt
Add Revise to Retain + Rewind (ablation)TriRE · Seq-CIFAR100 Class-ILaverage top-1 accuracy (%): 43.03 -> 43.91Improved
Add Revise to Retain + Rewind (ablation)TriRE · Seq-TinyImageNet Class-ILaverage top-1 accuracy (%): 16.25 -> 20.14Improved
Add Revise to Retain + Rewind (ablation)TriRE · Seq-TinyImageNet Task-ILaverage top-1 accuracy (%): 48.89 -> 55.95Improved
Add Rewind to Retain (ablation)TriRE · Seq-CIFAR100 Class-ILaverage top-1 accuracy (%): 38.01 -> 43.03Improved
Add Rewind to Retain (ablation)TriRE · Seq-TinyImageNet Class-ILaverage top-1 accuracy (%): 11.54 -> 16.25Improved
Add Rewind to Retain (ablation)TriRE · Seq-TinyImageNet Task-ILaverage top-1 accuracy (%): 40.22 -> 48.89Improved
Add Revise to Retain (ablation)TriRE · Seq-CIFAR100 Class-ILaverage top-1 accuracy (%): 38.01 -> 33.08Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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