Skip to content

[ACM Multimedia 2020] MPGAN. Rethinking Generative Zero-Shot Learning: An Ensemble Learning Perspective for Recognising Visual Patches

Notifications You must be signed in to change notification settings

uqzhichen/MPGAN

Repository files navigation

MPGAN

code for the paper in ACM Multimedia 2020: Rethinking Generative Zero-Shot Learning: An Ensemble Learning Perspective for Recognising Visual Patches

dataset:

You can download the dataset CUBird and NABird put the uncompressed dta to the folder "data"

Raw wikipedia artical data:

Raw wikipedia article data of CUBird and NABird, as well as detailed merging information of NABird, can be obtained here.

Reproduce results

CUBird SCS mode && SCE mode

python run_trainer.py --splitmode easy --dataset CUB2011

python run_trainer.py --splitmode hard --dataset CUB2011

NABird SCS mode && SCE mode python run_trainer.py --splitmode easy --dataset NABird

python run_trainer.py --splitmode hard --dataset NABird

About

[ACM Multimedia 2020] MPGAN. Rethinking Generative Zero-Shot Learning: An Ensemble Learning Perspective for Recognising Visual Patches

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages