AI Paper Atlas

Research map / Continual learning / Online and replay-based

Information Bottleneck Based Data Correction in Continual Learning

Shuai Chen, mingyi zhang, Junge Zhang, Kaiqi Huang

ECCV 2024 · Continual learning › Online and replay-based · approach: Unified and unsupervised continual frameworks · 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
add IBCL to ERER · Split CIFAR-100 (buffer 200)average accuracy: 14.35 -> 23.98Improved
add IBCL to X-DERX-DER · Split CIFAR-10 (buffer 500)average accuracy: 68.10 -> 74.14Improved
add IBCL to DER++DER++ · Split ImageNet-100 (buffer 2000)average accuracy: 58.05 -> 59.92Improved
add IBDS (unsampled data surrogate) to ER-ACE (ablation)ER-ACE · Split CIFAR-100 (buffer 200)average accuracy: 26.28 -> 30.44Improved
add IBTA (task-agnostic constraint) to ER-ACE (ablation)ER-ACE · Split CIFAR-100 (buffer 200)average accuracy: 26.28 -> 27.36Improved
add IBTA on top of IBDS to form full IBCL (ablation)DER++ · Split CIFAR-100 (buffer 200)average accuracy: 31.53 -> 33.82Improved
add IBCL versus adding DualHSIC to DER++DER++ · Split CIFAR-10 (buffer 100)average accuracy: 64.98 -> 66.41Improved
add sSGD regularization to ER-ACEER-ACE · Split miniImageNet (buffer 5000)average accuracy: 27.92 -> 24.12Hurt
add IBCL to fine-tuning with no bufferFine-tuning · CKA analysisfeature similarityImproved

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