AI Paper Atlas

Research map / Continual learning / Domain and prompt-based

Sequential Mastery of Multiple Visual Tasks: Networks Naturally Learn to Learn and Forget to Forget

Guy Davidson, Michael C. Mozer

CVPR 2020 · Continual learning › Domain and prompt-based · approach: Domain-incremental learning with memory · 17 citations (OpenAlex)

Check 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
Learn additional related tasks before introducing the next taskStandard CNN, sequential training · Synthetic visual tasks, episodes 3–10trials to criterionImproved
Repeatedly retrain earlier tasks across episodesStandard CNN, sequential training · Synthetic visual tasks, episodes 1–10trials to criterionImproved
Add task-specific learned biases to the first convolutional layer (ablation)Standard CNN, sequential training · Synthetic visual tasks, especially episodes 2–3trials to criterionImproved
Add task-specific learned biases to the first convolutional layer (ablation)Standard CNN, sequential training · Synthetic visual tasks, later episodestrials to criterionNo clear effect
Mix tasks from color, shape, and texture dimensions instead of using one dimension (ablation)Standard CNN, sequential training · Synthetic visual tasks, episodes 1–10trials to criterionNo clear effect
Mix tasks from different dimensions (ablation)Standard CNN, sequential training · Synthetic visual tasks, first two episodesbackward interferenceImproved
Apply MAML-style meta-training, splitting examples between task learning and meta-training (ablation)Standard CNN, sequential training · Synthetic visual tasks, episodes 1–10trials to criterionHurt
Use alternative ratio or power curricula rather than the balanced old/new split (ablation)Standard CNN, sequential training · Synthetic visual tasks, episodes 1–10trials to criterionNo clear effect
Train on all ten tasks simultaneously instead of introducing tasks sequentially (ablation)Standard CNN · Color and texture taskstrials to criterionHurt
Train on all ten tasks simultaneously instead of introducing tasks sequentially (ablation)Standard CNN · Shape taskstrials to criterionNo clear effect
Fit an exponential rather than power-law forgetting curve (ablation)Forgetting-curve model · Synthetic visual tasks, held-out forgetting curvesheld-out MSE: 0.0232 -> 0.0192Improved
Fit an exponential rather than power-law forgetting curve (ablation)Forgetting-curve model · Synthetic visual tasks, training forgetting curvestraining MSE: 0.0045 -> 0.0198Hurt

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