AGA: Attribute Guided Augmentation

12/08/2016
by   Mandar Dixit, et al.
0

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.

READ FULL TEXT

page 1

page 5

page 7

research
01/13/2018

Feature Space Transfer for Data Augmentation

The problem of data augmentation in feature space is considered. A new a...
research
06/12/2018

Delta-encoder: an effective sample synthesis method for few-shot object recognition

Learning to classify new categories based on just one or a few examples ...
research
09/12/2016

Reliable Attribute-Based Object Recognition Using High Predictive Value Classifiers

We consider the problem of object recognition in 3D using an ensemble of...
research
12/04/2021

Implicit Data Augmentation Using Feature Interpolation for Diversified Low-Shot Image Generation

Training of generative models especially Generative Adversarial Networks...
research
10/09/2019

A Closer Look At Feature Space Data Augmentation For Few-Shot Intent Classification

New conversation topics and functionalities are constantly being added t...
research
08/16/2020

Bowtie Networks: Generative Modeling for Joint Few-Shot Recognition and Novel-View Synthesis

Generative modeling has recently shown great promise in computer vision,...
research
03/19/2015

Learning Hypergraph-regularized Attribute Predictors

We present a novel attribute learning framework named Hypergraph-based A...

Please sign up or login with your details

Forgot password? Click here to reset