AGA: Attribute Guided Augmentation

TL;DR

This paper introduces Attribute Guided Augmentation (AGA), a novel method for synthesizing attribute-controlled data in feature space to improve one-shot recognition tasks using external annotated datasets.

Contribution

We propose a deep encoder-decoder architecture for attribute-guided data augmentation in feature space, enhancing one-shot recognition performance without requiring attribute annotations in the target data.

Findings

Significant improvement in one-shot object recognition accuracy.

Effective augmentation using external depth and pose data.

Versatility in transfer-learning and scene recognition tasks.

Abstract

We consider the problem of data augmentation, i.e., generating artificial samples to extend a given corpus of training data. Specifically, we propose attributed-guided augmentation (AGA) which learns a mapping that allows to synthesize data such that an attribute of a synthesized sample is at a desired value or strength. This is particularly interesting in situations where little data with no attribute annotation is available for learning, but we have access to a large external corpus of heavily annotated samples. While prior works primarily augment in the space of images, we propose to perform augmentation in feature space instead. We implement our approach as a deep encoder-decoder architecture that learns the synthesis function in an end-to-end manner. We demonstrate the utility of our approach on the problems of (1) one-shot object recognition in a transfer-learning setting where we have no prior knowledge of the new classes, as well as (2) object-based one-shot scene recognition. As external data, we leverage 3D depth and pose information from the SUN RGB-D dataset. Our experiments show that attribute-guided augmentation of high-level CNN features considerably improves one-shot recognition performance on both problems.