AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Meta Learning on a Sequence of Imbalanced Domains With Difficulty Awareness

Zhenyi Wang, Tiehang Duan, Le Fang, Qiuling Suo, Mingchen Gao

ICCV 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Optimization-based domain generalization · 18 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 M2D3 memory management (distribution and difficulty aware) in place of reservoir sampling (ablation)PNet-RS · Imbalanced 6-domain meta-learning benchmark, 5-way 1-shotaccuracy (%): 34.68 -> 38.85Improved
add M2D3 memory management in place of reservoir sampling (ablation)PNet-RS · Imbalanced 6-domain meta-learning benchmark, 5-way 5-shotaccuracy (%): 53.69 -> 57.95Improved
add adaptive memory task sampling (PETS) (ablation)PNet with M2D3 · Imbalanced 6-domain meta-learning benchmark, 5-way 1-shotaccuracy (%): 38.85 -> 41.10Improved
add adaptive memory task sampling (PETS) (ablation)PNet with M2D3 · Imbalanced 6-domain meta-learning benchmark, 5-way 5-shotaccuracy (%): 57.95 -> 60.37Improved
use proposed method instead of reservoir samplingPrototypical Network · Imbalanced 6-domain meta-learning benchmark, 5-way 5-shotaccuracy (%): 53.69 -> 60.37Improved
use proposed method instead of reservoir samplingANIL · Imbalanced 6-domain meta-learning benchmark, 5-way 5-shotaccuracy (%): 48.72 -> 53.65Improved
use proposed method instead of reservoir samplingANIL · Imbalanced 6-domain meta-learning benchmark, 5-way 1-shotaccuracy (%): 32.11 -> 34.91Improved
increase memory capacity from 200 to 500 batches (ablation)PNet-Ours · Imbalanced 6-domain meta-learning benchmark, 5-way 5-shotaccuracy (%): 59.86 -> 61.05Improved
increase memory capacity from 200 to 500 batches (ablation)PNet-RS · Imbalanced 6-domain meta-learning benchmark, 5-way 5-shotaccuracy (%): 53.29 -> 55.95Improved
add continual learning replay methods (GSS, AGEM, MIR, MER) to PNet instead of RSPNet-RS · Imbalanced 6-domain meta-learning benchmark, 5-way 1-shotaccuracy (%): 34.68 -> 34.07 (AGEM), 36.15 (GSS)Mixed
replace sequential training with proposed methodPNet-Sequential · Imbalanced 6-domain meta-learning benchmark, 5-way 1-shotaccuracy (%): 31.82 -> 41.10Improved

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