Implementation of Repurposing GANs for One-shot Semantic Part Segmentation

Repurposing GANs

A minimal implementation of Repurposing GANs for One-shot Semantic Part Segmentation.

111058929-2ba3fd00-84d5-11eb-964e-a29f374729da

w/ interactive jupyter notebook labelling tool

111059840-d6b7b500-84db-11eb-864a-6a852f679336

One-Shot Segmentation

Results from CNN-S trained for 100 steps with a single annotated image

111058934-35c5fb80-84d5-11eb-8142-2a6ad2e70be0

111059843-da4b3c00-84db-11eb-865b-921d91ed3614

111059326-141a4380-84d8-11eb-86cb-fa2c7d19b8d6

label_sample

One-Shot Segmentation
Results from CNN-S trained for 100 steps with a single annotated image

 

 

 

To finish reading, please visit source site