AI Paper Atlas

Research map / Continual learning / Online and replay-based

Continual Unsupervised Representation Learning

Dushyant Rao, Francesco Visin, Andrei Rusu, Razvan Pascanu, Yee Whye Teh, Raia Hadsell

NeurIPS 2019 · Continual learning › Online and replay-based · approach: Unified and unsupervised continual frameworks · 84 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 dynamic expansion rather than a fixed mixture size (ablation)CURL · MNIST sequentialCluster accuracy: 51% -> 77%Improved
Add mixture generative replay (ablation)CURL · MNIST sequentialCluster acc (%): 45.35_{\pm 1.50} -> 77.74_{\pm 1.37}Improved
Add mixture generative replay (ablation)CURL · Omniglot sequentialCluster acc (%): 13.36_{\pm 1.06} -> 13.21_{\pm 0.53}No clear effect
Snapshot at 0.1T intervals rather than T intervals (ablation)CURL with MGR · MNIST sequentialCluster acc (%): 77.74_{\pm 1.37} -> 49.14_{\pm 3.95}Hurt
Snapshot before dynamic expansion instead of at T intervals (ablation)CURL with MGR · MNIST sequentialCluster acc (%): 77.74_{\pm 1.37} -> 57.76_{\pm 1.43}Hurt
Add self-supervised component-consistency loss (ablation)CURL with MGR · MNIST sequentialCluster acc (%): 77.74_{\pm 1.37} -> 69.27_{\pm 1.46}Hurt
Add self-supervised component-consistency loss (ablation)CURL with MGR · Omniglot sequentialCluster acc (%): 13.21_{\pm 0.53} -> 11.32_{\pm 0.52}Improved
Use continuous drift rather than abrupt sequential class changes (ablation)CURL with MGR (fixed snapshots) · MNISTCluster acc (%): 77.74_{\pm 1.37} -> 79.38_{\pm 4.26}Improved
Use continuous drift rather than abrupt sequential class changes (ablation)CURL with MGR (dynamic snapshots) · OmniglotCluster acc (%): 12.74_{\pm 0.60} -> 13.54_{\pm 0.35}Improved
Increase the expansion threshold, allowing more components (ablation)CURL · MNIST sequentialCluster accuracy: 12 to 71 components; up to 84%Mixed
Train CURL on shuffled i.i.d data instead of sequential dataCURL · MNIST10-NN error (%): 4.23_{\pm 0.30} vs 4.50_{\pm 0.34}No clear effect

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