AI Paper Atlas

Research map / Continual learning / Online and replay-based

CODE-CL: Conceptor-Based Gradient Projection for Deep Continual Learning

Marco P. E. Apolinario, Sakshi Choudhary, Kaushik Roy

ICCV 2025 · Continual learning › Online and replay-based · approach: Unified and unsupervised continual frameworks · 3 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
free K shared directions (K=80) vs none (K=0) (ablation)CODE-CL · 5-DatasetsACC (%): 91.67 -> 93.32Improved
free K shared directions (K=80) vs none (K=0) (ablation)CODE-CL · 5-DatasetsBWT (%): -1.36 -> -0.25Improved
increase free dimensions K beyond 20 (ablation)CODE-CL · Split CIFAR100, Split miniImageNetACCImproved
increase aperture alpha (ablation)CODE-CL · Split CIFAR100, Split miniImageNetBWTImproved
increase aperture alpha from 4 to 16 (ablation)CODE-CL · 5-DatasetsACC (%): 93.32 -> 93.46No clear effect
raise threshold epsilon from 0.5 to 0.8 (ablation)CODE-CL · Split CIFAR100ACC (%): 77.21 -> 75.71Hurt
lower threshold epsilon from 0.5 to 0.2 (ablation)CODE-CL · Split MiniImageNetACC (%): 68.83 -> 68.61No clear effect
conceptor-based pseudo-orthogonal projection with selective release of shared directions vs SGPSplit CIFAR100 · Split CIFAR100relative FWT: 4.74 -> 5.92Improved
CODE-CL vs SGP on overlapping classesOL-CIFAR100 · OL-CIFAR100ACC (%): 75.00 -> 76.89Improved
CODE-CL vs TRGP and CUBER on memory and timeSplit CIFAR100 · Split CIFAR100GPU memory and runtimeImproved
CODE-CL vs HAT/TRGP on forgettingSplit CIFAR100 · Split CIFAR100BWT (%): -0.1 -> -1.1No clear effect

Later papers that compared with this method

1 later accepted paper reports CODE-CL as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.

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