AI Paper Atlas

Research map / Continual learning / Online and replay-based

Lifelong Infinite Mixture Model Based on Knowledge-Driven Dirichlet Process

Fei Ye, Adrian G. Bors

ICCV 2021 · Continual learning › Online and replay-based · approach: Unified and unsupervised continual frameworks · 31 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
use LIMix mixture instead of single-model LGMLGM · MSFIR unsupervised (avg)MSE: 190.38 -> 28.97Improved
use LIMix instead of BatchEnsembleBatchEnsemble · MSFIR unsupervised (avg)MSE: 31.91 -> 28.97Improved
use LIMix instead of BatchEnsembleBatchEnsemble · MSFIR unsupervised (avg)PSNR: 19.31 -> 19.86Improved
use full LIMix instead of compact Student (ablation)Student · MSFIR unsupervised (avg)MSE: 163.45 -> 28.97Improved
use LIMix instead of BatchEnsembleBatchEnsemble · MSFIRC classification (avg)accuracy: 83.47 -> 84.18Improved
use LIMix instead of BatchEnsembleBatchEnsemble · MSFIRC classification on MNISTaccuracy: 99.40 -> 91.16Hurt
use LIMix instead of BatchEnsembleBatchEnsemble · MSFIRC classification on SVHNaccuracy: 74.46 -> 82.60Improved
use LIMix instead of CURLCURL · MSFIRC classification on CIFAR10accuracy: 67.34 -> 54.66Hurt
use LIMix instead of FROMPFROMP · Permuted MNISTaccuracy: 94.9 -> 96.46Improved
use LIMix instead of FROMPFROMP · Split MNISTaccuracy: 99.0 -> 99.21Improved
reduce LIMix components from 10 to 7 (ablation)LIMix · Permuted MNISTaccuracy: 96.46 -> 88.78Hurt
reduce LIMix components from 5 to 3 (ablation)LIMix · Split MNISTaccuracy: 99.21 -> 91.37Hurt

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