AI Paper Atlas

Research map / Continual learning / Class-incremental

Overcoming Catastrophic Forgetting With Unlabeled Data in the Wild

Kibok Lee, Kimin Lee, Jinwoo Shin, Honglak Lee

ICCV 2019 · Continual learning › Class-incremental · approach: Class-balanced knowledge retention · 220 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 unlabeled external dataGD · CIFAR-100 (task size 10)ACC: 65.0 -> 68.1Improved
add unlabeled external dataGD · CIFAR-100 (task size 10)FGT: 12.1 -> 7.7Improved
add unlabeled external dataE2E · ImageNet 32x32 (task size 10)ACC: 50.8 -> 52.8Improved
add current-task teacher C to previous model P (ablation)GD · CIFAR-100 (task size 10)ACC: 62.9 -> 67.0Improved
add ensemble reference Q to P and C (ablation)GD · CIFAR-100 (task size 10)ACC: 67.0 -> 68.1Improved
add ensemble reference Q to P and C (ablation)GD · CIFAR-100 (task size 10)FGT: 10.7 -> 7.7Improved
train C by distillation (dst) instead of direct hard-label loss (cls) (ablation)GD · CIFAR-100 (task size 10)ACC: 62.9 -> 66.2Improved
add confidence loss to teacher C (ablation)GD · CIFAR-100 (task size 10)ACC: 66.2 -> 67.0Improved
add fine-tuning with data weighting (FT-DW) (ablation)GD · CIFAR-100 (task size 10)FGT: 11.5 -> 7.7Improved
fine-tuning with data weighting instead of FT-DSet (ablation)GD · CIFAR-100 (task size 10)ACC: 67.2 -> 68.1Improved
sample random OOD data in addition to previous-task-like data (ablation)GD · CIFAR-100 (task size 10)ACC: 66.0 -> 68.1Improved
sample OOD data by previous-model prediction instead of randomly (ablation)GD · CIFAR-100 (task size 10)ACC: 68.1 -> 65.7Hurt

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