AI Paper Atlas

Research map / Continual learning / Online and replay-based

Class-Incremental Continual Learning Into the eXtended DER-Verse

Matteo Boschini, Lorenzo Bonicelli, Pietro Buzzega, Angelo Porrello, Simone Calderara

TPAMI 2022 · Continual learning › Online and replay-based · approach: Unified and unsupervised continual frameworks · 153 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
add memory logit update (future past) (ablation)X-DER · Split CIFAR-100 (buffer 500)FAA: 42.67 -> 49.93Improved
add memory logit update (future past) (ablation)X-DER · Split CIFAR-100 (buffer 2000)FAA: 56.55 -> 59.14Improved
add memory logit update (future past) (ablation)X-DER · Split NTU-60FAA: 57.66 -> 64.86Improved
add pre-allocated future heads with contrastive preparation (ablation)X-DER · Split CIFAR-100 (buffer 500)FAA: 45.61 -> 49.93Improved
add pre-allocated future heads with contrastive preparation (ablation)X-DER · Split miniImageNet (buffer 2000)FAA: 21.71 -> 28.19Improved
add pre-allocated future heads with contrastive preparation (ablation)X-DER · Split NTU-60FAF: 9.80 -> 9.95Improved
use contrastive future preparation instead of fixed RPC heads (ablation)X-DER · Split CIFAR-100 (buffer 500)FAA: 48.53 -> 49.93Improved
use contrastive future preparation instead of CE on future heads (ablation)X-DER · Split CIFAR-100 (buffer 500)FAA: 47.67 -> 49.93Improved
replace DER++ with X-DERDER++ · Split CIFAR-100 (buffer 500)FF: 50.54 -> 19.90Improved
add memory logit update (ablation)X-DER · CIFAR-100 superclassSS-ERR: 0.64 -> 0.57Improved
add memory logit update (ablation)X-DER · CIFAR-100 superclassSS-NLL: 2.14 -> 1.83Improved
train from X-DER buffer logits instead of DER++ bufferX-DER · Split CIFAR-100 and miniImageNetbuffer-only accuracy: 6% average gain (logits alone), 6.25% (with labels)Improved

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