AI Paper Atlas

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

Few-Shot Partial Multi-View Learning

Yuan Zhou, Yanrong Guo, Shijie Hao, Richang Hong, Jiebo Luo

TPAMI 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Uncertainty-aware multi-view learning · 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
add UGDA on top of PTMAPPTMAP · Cub-googlenet-doc2vec 3-way 1-shot, view-missing rate 0.5accuracy (%): 56.87 -> 77.52Improved
add UGDA on top of PTMAPPTMAP · Caltech102 5-way 1-shot, view-missing rate 0.5accuracy (%): 30.99 -> 40.76Improved
add UGDA on top of PTMAP with no missing viewsPTMAP · Caltech102 5-way 1-shot, view-missing rate 0accuracy (%): 59.58 -> 56.58Hurt
add UGDA on top of RFSRFS · Animal 5-way 1-shot, view-missing rate 0.5accuracy (%): 48.21 -> 63.32Improved
add UGDA on top of RFSRFS · ORL 5-way 1-shot, view-missing rate 0accuracy (%): 86.51 -> 90.95Improved
use UGDA instead of the strongest few-shot baseline at eta=0.5PTMAP · Scene15 3-way 1-shotaccuracy (%): 50.68 -> 62.17Improved
use UGDA instead of PTMAP with complete viewsPTMAP · Handwritten 3-way 1-shot, view-missing rate 0accuracy (%): 89.14 -> 89.08No clear effect
use UGDA instead of COMPLETER at high missing rateCOMPLETER · Scene15 3-way 1-shot, view-missing rate 0.5accuracy (%): 43.20 -> 62.17Improved
use UGDA instead of ICMSC at high missing rateICMSC · ORL 5-way 1-shot, view-missing rate 0.5accuracy (%): 20.02 -> 64.78Improved
increase view-missing rate from 0 to 0.5 for UGDAUGDA · Cub-googlenet-doc2vec 3-way 1-shotaccuracy (%): 95.59 -> 76.69Hurt

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