AI Paper Atlas

Research map / Continual learning / Online and replay-based

C-Flat++: Towards a More Efficient and Powerful Framework for Continual Learning

IJCV 2026 · Continual learning › Online and replay-based · approach: Unified and unsupervised continual frameworks

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
add C-Flat to the optimizerReplay · CIFAR-100 B0_Inc10average accuracy: 58.09 -> 59.42Improved
add C-Flat to the optimizeriCaRL · CIFAR-100 B0_Inc10average accuracy: 58.80 -> 59.75Improved
add C-Flat to the optimizerWA · CIFAR-100 B0_Inc10average accuracy: 65.63 -> 67.00Improved
add C-Flat to the optimizerPODNet · CIFAR-100 B0_Inc10average accuracy: 55.60 -> 57.00Improved
add C-Flat to the optimizerDER · CIFAR-100 B0_Inc10average accuracy: 70.13 -> 71.35Improved
add C-Flat to the optimizerFOSTER · CIFAR-100 B0_Inc10average accuracy: 65.84 -> 67.27Improved
add C-Flat to the optimizerMEMO · CIFAR-100 B0_Inc10average accuracy: 68.49 -> 69.48Improved
add C-Flat to FOSTER on CUBFOSTER · CUB B0_Inc20average accuracy: 31.84 -> 29.28Hurt
add C-Flat to WA on ImageNet-100WA · ImageNet-100 B50_Inc10average accuracy: 75.07 -> 74.03Hurt
C-Flat++ (adaptive 25.1% sharpness updates) instead of full C-FlatC-Flat · Hybrid SGD/C-Flat study (avg accuracy)average accuracy: 70.79 -> 70.39No clear effect
replace 25% of SGD steps with C-Flat (ablation)SGD · Hybrid SGD/C-Flat study (avg accuracy)average accuracy: 69.13 -> 69.91Improved
replace SGD flatness term FS with C-FlatFS-DGPM · FS-DGPM series, average accuracyaverage accuracy: 73.14 -> 73.72Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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