AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Task-Level Self-Supervision for Cross-Domain Few-Shot Learning

Wang Yuan, Zhizhong Zhang, Cong Wang, Haichuan Song, Yuan Xie, Lizhuang Ma

AAAI 2022 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Fine-tuning strategies for few-shot · 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
Use TL-SS with task variants, consistency and metric-alignment losses alongside HAE (ablation)T3S · miniImageNet→CUB, 5-way 5-shotaccuracy: 64.87 -> 69.16Improved
Add instance-level augmentation and metric-alignment loss (ablation)HAE · miniImageNet→CUB, 5-way 5-shotaccuracy: 64.87 -> 66.55Improved
Add class-level permutation to instance augmentation (ablation)HAE with metric-alignment loss · miniImageNet→CUB, 5-way 5-shotaccuracy: 66.55 -> 68.30Improved
Add task consistency loss Lt (ablation)HAE with instance augmentation, class permutation and Lm · miniImageNet→CUB, 5-way 5-shotaccuracy: 68.30 -> 69.16Improved
Replace average task-context pooling with 3D CNN context modeling (ablation)HAE · miniImageNet→CUB, 5-way 5-shotaccuracy: 63.41 -> 68.30Improved
Use T3S rather than the strongest listed baselineCross-domain few-shot classification · miniImageNet→CUB, 5-way 1-shotaccuracy: 47.47 -> 45.92Hurt
Use T3S rather than the strongest listed baselineCross-domain few-shot classification · miniImageNet→Cars, 5-way 1-shotaccuracy: 31.61 -> 33.22Improved
Use T3S rather than the strongest listed baselineCross-domain few-shot classification · miniImageNet→Places, 5-way 1-shotaccuracy: 55.77 -> 55.83Improved
Use T3S rather than the strongest listed baselineCross-domain few-shot classification · miniImageNet→EuroSAT, 5-way 1-shotaccuracy: 64.00 -> 65.73Improved
Use T3S rather than the strongest listed baselineCross-domain few-shot classification · miniImageNet→CUB, 5-way 5-shotaccuracy: 64.97 -> 69.16Improved
Use T3S rather than the strongest listed baselineCross-domain few-shot classification · miniImageNet→Cars, 5-way 5-shotaccuracy: 47.77 -> 49.82Improved
Use T3S rather than the strongest listed baselineCross-domain few-shot classification · miniImageNet→Places, 5-way 5-shotaccuracy: 71.82 -> 76.33Improved

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