AI Paper Atlas

Research map / Continual learning / Online and replay-based

Continual Learning on Noisy Data Streams via Self-Purified Replay

Chris Dongjoo Kim, Jinseo Jeong, Sangwoo Moon, Gunhee Kim

ICCV 2021 · Continual learning › Online and replay-based · approach: Replay buffer construction and update · 46 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 the Self-Centered filter to Self-Replay (ablation)Self-Replay · MNIST symmetric noise 60%accuracy: 43.0 -> 84.8Improved
add the Self-Centered filter to Self-Replay (ablation)Self-Replay · CIFAR-10 symmetric noise 60%accuracy: 22.4 -> 40.0Improved
add Self-Replay to the Self-Centered filter (ablation)Self-Centered filter · MNIST symmetric noise 20%accuracy: 80.1 -> 85.4Improved
add the Self-Centered filter to Self-Replay (ablation)Self-Replay · WebVision (real noise)accuracy: 48.0 -> 40.0Hurt
add stochastic ensemble to the Self-Centered filter (ablation)non-stochastic Self-Centered filter · MNIST symmetric noise 20% (filtered noise %)filtered noisy label percentage: 79.5 -> 96.0Improved
add stochastic ensemble to the Self-Centered filter (ablation)non-stochastic Self-Centered filter · CIFAR-10 symmetric noise 20% (filtered noise %)filtered noisy label percentage: 50.5 -> 75.5Improved
use the Self-Centered filter instead of AUMAUM · CIFAR-10 symmetric noise 20% (filtered noise %)filtered noisy label percentage: 36.0 -> 75.5Improved
add L2R noisy label techniqueGDumb · MNIST symmetric noise 20%accuracy: 70.0 -> 65.2Hurt
add L2R noisy label techniqueGDumb · MNIST symmetric noise 60%accuracy: 36.0 -> 42.3Improved
add L2R noisy label techniqueCRS · MNIST symmetric noise 20%accuracy: 58.6 -> 80.6Improved
use SPR instead of GDumb + SLGDumb + SL · CIFAR-100 random symmetric noise 20%accuracy: 19.3 -> 21.5Improved
use SPR instead of GDumb + JoCoRGDumb + JoCoR · CIFAR-100 random symmetric noise 60%accuracy: 6.1 -> 18.1Improved

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