VOCABULARY-INFORMED VISUAL FEATURE AUGMENTATION FOR ONE-SHOT LEARNING

jianqi ma, hangyu lin, yinda zhang, yanwei fu, xiangyang xue

Abstract: A natural solution for one-shot learning is to augment training data to handle the data deficiency problem. However, directly augmenting in the image domain may not necessarily generate training data that sufficiently explore the intra-class space for one-shot classification. Inspired by the recent vocabulary-informed learning, we propose to generate synthetic training data with the guide of the semantic word space. Essentially, we train an auto-encoder as a bridge to enable the transformation between the image feature space and the semantic space. Besides directly augmenting image features, we transform the image features to semantic space using the encoder and perform the data augmentation. The decoder then synthesizes the image features for the augmented instances from the semantic space. Experiments on three datasets show that our data augmentation method effectively improves the performance of one-shot classification. An extensive study shows that data augmented from semantic space are complementary with those from the image space, and thus boost the classification accuracy dramatically. Source code and dataset will be available.

Keywords: vocabulary-informed learning, data augmentation