AI Paper Atlas

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

Learning Classifiers for Target Domain with Limited or No Labels

Pengkai Zhu, Hanxiao Wang, Venkatesh Saligrama

ICML 2019 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 8 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
learn encoder jointly on source and unlabeled target data with pseudo-label cross-entropy (joint pi) vs source-only (ablation)LDVA · SVHN->MNISTaccuracy (%): 82.4 -> 95.2Improved
joint pi vs source pi (ablation)LDVA · MNIST->USPSaccuracy (%): 94.8 -> 98.8Improved
joint pi vs source pi (ablation)LDVA · USPS->MNISTaccuracy (%): 96.1 -> 96.8Improved
add calibrated stacking (CS) to LDVA (ablation)LDVA · CUB GZSLharmonic mean H (%): 48.4 -> 66.0Improved
add calibrated stacking (CS) (ablation)LDVA · AWA2 GZSLharmonic mean H (%): 57.2 -> 67.3Improved
add calibrated stacking (CS) (ablation)LDVA · aPY GZSLharmonic mean H (%): 36.6 -> 51.2Improved
add calibrated stacking (CS) lowers seen-class accuracy to balance (ablation)LDVA · CUB GZSLseen accuracy tr (%): 87.5 -> 74.6Hurt
add calibrated stacking raises unseen accuracy (ablation)LDVA · CUB GZSLunseen accuracy ts (%): 33.4 -> 59.2Improved
LDVA+CS vs second-best LSDLDVA + CS · CUB GZSLharmonic mean H (%): 56.1 -> 66.0Improved
LDVA+CS vs second-best CADA-VAELDVA + CS · AWA2 GZSLharmonic mean H (%): 63.9 -> 67.3Improved
LDVA nearest-neighbour classifier without meta-training vs EA-FSLLDVA · miniImageNet 5-way 5-shotaccuracy (%): 78.4 -> 78.7Improved
LDVA vs LEOLDVA · miniImageNet 5-way 1-shotaccuracy (%): 61.7 -> 61.7No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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