AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Towards Context-Agnostic Learning Using Synthetic Data

Charles Jin, Martin Rinard

NeurIPS 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Learning from unlabeled and positive-unlabeled data · 0 citations (OpenAlex)

Read the paper

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 PGD refinement to random-context synthetic training (ablation)Context-agnostic classifier trained from one synthetic example per class · GTSRB testaccuracy (%): 72.1 -> 86.4Improved
Add previous-image context bias correction to random-context training (ablation)Context-agnostic classifier trained from Picto · GTSRB testaccuracy (%): 72.1 -> 87.3Improved
Combine bias correction with PGD refinement (ablation)Context-agnostic classifier trained from Picto · GTSRB testaccuracy (%): 72.0 -> 95.9Improved
Add PGD refinement to random-context synthetic training (ablation)Context-agnostic classifier trained from Digit · MNISTaccuracy (%): 88.3 -> 89.7Improved
Add previous-image context bias correction to random-context training (ablation)Context-agnostic classifier trained from Digit · MNISTaccuracy (%): 81.9 -> 89.2Improved
Combine bias correction with PGD refinement (ablation)Context-agnostic classifier trained from Digit · MNISTaccuracy (%): 81.9 -> 90.2Improved
Add PGD refinement to random-context synthetic training (ablation)Context-agnostic classifier trained from Omnifont · Omniglot 20-wayaccuracy (%): 69.8 -> 90.8Improved
Add previous-image context bias correction to random-context training (ablation)Context-agnostic classifier trained from Omnifont · Omniglot 20-wayaccuracy (%): 71.9 -> 80.5Improved
Combine bias correction with PGD refinement (ablation)Context-agnostic classifier trained from Omnifont · Omniglot 20-wayaccuracy (%): 71.9 -> 92.2Improved
Reuse random backgrounds as contexts (ablation)Synthetic classifier trained from Picto · GTSRB testaccuracy (%): 72.0 -> 72.1No clear effect
Reuse random backgrounds as contexts (ablation)Synthetic classifier trained from Omnifont · Omniglot 20-wayaccuracy (%): 71.9 -> 69.8Hurt
Remove bias correction from the full method (ablation)Context-agnostic classifier trained from Picto · GTSRB testaccuracy (%): 95.9 -> 86.4Hurt

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