VCE: Variational Convertor-Encoder for One-Shot Generalization
This addresses one-shot generalization for image transformation tasks, but appears incremental as it builds on existing VAE variants.
The paper tackles one-shot generalization by proposing Variational Convertor-Encoder (VCE), which converts images to various styles without additional training for new tasks, and improves VAE performance with a large margin variant (LMVAE) to filter blurred points. Results on Omniglot datasets show the model produces more realistic and diverse images.
Variational Convertor-Encoder (VCE) converts an image to various styles; we present this novel architecture for the problem of one-shot generalization and its transfer to new tasks not seen before without additional training. We also improve the performance of variational auto-encoder (VAE) to filter those blurred points using a novel algorithm proposed by us, namely large margin VAE (LMVAE). Two samples with the same property are input to the encoder, and then a convertor is required to processes one of them from the noisy outputs of the encoder; finally, the noise represents a variety of transformation rules and is used to convert new images. The algorithm that combines and improves the condition variational auto-encoder (CVAE) and introspective VAE, we propose this new framework aim to transform graphics instead of generating them; it is used for the one-shot generative process. No sequential inference algorithmic is needed in training. Compared to recent Omniglot datasets, the results show that our model produces more realistic and diverse images.