VCE: Variational Convertor-Encoder for One-Shot Generalization

TL;DR

The paper introduces VCE, a novel variational architecture for one-shot image style transfer and generalization to unseen tasks without extra training, enhancing VAE performance with a new algorithm.

Contribution

Proposes VCE, a new variational convertor-encoder architecture that enables one-shot style transfer and generalization, along with the large margin VAE algorithm to improve image filtering.

Findings

VCE produces more realistic images than existing models.

The model demonstrates effective one-shot generalization to new tasks.

No sequential inference is required during training.

Abstract

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.