AI Paper Atlas

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

Task-aware Adaptive Learning for Cross-domain Few-shot Learning

Yurong Guo, Ruoyi Du, Yuan Dong, Timothy Hospedales, Yi-Zhe Song, Zhanyu Ma

ICCV 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Conditional distribution alignment · 20 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
replace fixed task-specific adapter with task-adaptive RL-learned adapter configurationTA2-Net vs TSA · Meta-Dataset multi-domain, unseen averageaccuracy (%): 78.1 -> 79.1Improved
replace fixed task-specific adapter with task-adaptive configuration in single-domain trainingTA2-Net vs TSA · Meta-Dataset single-domain, unseen averageaccuracy (%): 71.9 -> 75.0Improved
train adapter gate with reinforcement learning instead of episodic training (ablation)TA2-Net · Meta-Dataset multi-domain, unseenaccuracy (%): 67.9 -> 72.6Improved
widen the task-specific adapter (parallel 1x1 conv) instead of deepening it (series) (ablation)Task-specific adapter · Meta-Dataset multi-domainaccuracyImproved
attach fixed task-specific adapter to backbone (no adaptive selection) (ablation)ResNet-18 backbone · Meta-Dataset seen domainsaverage accuracyHurt
attach fixed task-specific adapter to backbone (no adaptive selection) (ablation)ResNet-18 backbone · Meta-Dataset unseen domainsaverage accuracyImproved
increase max adapter width K from 1 to 3 (ablation)TA2-Net · Meta-Dataset five-shot, unseenaccuracy (%): 66.6 -> 70.5Improved
increase max adapter width K from 3 to 4 (ablation)TA2-Net · Meta-Dataset five-shot, unseenaccuracy (%): 70.5 -> 68.2Hurt
increase max adapter width K on seen domains (ablation)TA2-Net · Meta-Dataset five-shot, seenaccuracy (%): 75.4 -> 75.1 (K=1 to K=4)No clear effect
TA2-Net versus TSA on CIFAR-10 and TexturesTA2-Net · Meta-Dataset multi-domainaccuracy (%): CIFAR-10 82.9 -> 82.1; Textures 77.5 -> 77.4Mixed

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