Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
one-shot_learning [2019/01/12 11:05]
admin
one-shot_learning [2019/01/12 11:07]
admin
Line 205: Line 205:
 https://​arxiv.org/​abs/​1901.02199v1 FIGR: Few-shot Image Generation with Reptile https://​arxiv.org/​abs/​1901.02199v1 FIGR: Few-shot Image Generation with Reptile
  
-Our model successfully generates novel images on both MNIST and Omniglot with as little as 4 images from an unseen class. We further contribute FIGR-8, a new dataset for few-shot image generation, which contains 1,548,944 icons categorized in over 18,409 classes. Trained on FIGR-8, initial results show that our model can generalize to more advanced concepts (such as "​bird"​ and "​knife"​) from as few as 8 samples from a previously unseen class of images and as little as 10 training steps through those 8 images. ​+Our model successfully generates novel images on both MNIST and Omniglot with as little as 4 images from an unseen class. We further contribute FIGR-8, a new dataset for few-shot image generation, which contains 1,548,944 icons categorized in over 18,409 classes. Trained on FIGR-8, initial results show that our model can generalize to more advanced concepts (such as "​bird"​ and "​knife"​) from as few as 8 samples from a previously unseen class of images and as little as 10 training steps through those 8 images. ​ ​https://​github.com/​OctThe16th/​FIGR https://​github.com/​marcdemers/​FIGR-8