AI Paper Atlas

Research map / Continual learning / Online and replay-based

Random Path Selection for Continual Learning

Jathushan Rajasegaran, Munawar Hayat, Salman H Khan, Fahad Shahbaz Khan, Ling Shao

NeurIPS 2019 · Continual learning › Online and replay-based · approach: Unified and unsupervised continual frameworks · 69 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 distillation loss to single-path baseline (ablation)RPS-Net baseline · CIFAR-100accuracy: 37.97% -> 44.93%Improved
add controller phi(k, gamma) (ablation)single path + distillation · CIFAR-100accuracy: 44.93% -> 51.76%Improved
add multi-path random selection (ablation)single path + distillation + controller · CIFAR-100accuracy: 51.76% -> 58.48%Improved
use gamma=1 (iCaRL-style) instead of 2.5 (ablation)RPS-Net · CIFAR-100accuracyHurt
use gamma=8 instead of 2.5 (ablation)RPS-Net · CIFAR-100accuracy: 51% at task 10Mixed
increase number of paths (smaller J) (ablation)RPS-Net · CIFAR-100accuracyHurt
vary number of modules M (including saturated M=1) (ablation)RPS-Net · CIFAR-100accuracyNo clear effect
random path selection instead of genetic Binary Tournament Selection (ablation)RPS-Net on MNIST · MNIST 5 tasksaverage accuracy: 96.32% -> 96.52%No clear effect
RPS-Net instead of iCARLclass-incremental CIFAR-100 · CIFAR-100 10 classes per taskaccuracy: +7.3%Improved
RPS-Net instead of iCARLclass-incremental ImageNet · ImageNet 100 classes, 10 per tasktop-5 accuracy: +10.3%Improved
RPS-Net instead of iCARLbackward transfer · CIFAR-100BWT: -0.4602 -> -0.1462Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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