Image-to-Image Translation of Synthetic Samples for Rare Classes

by   Edoardo Lanzini, et al.

The natural world is long-tailed: rare classes are observed orders of magnitudes less frequently than common ones, leading to highly-imbalanced data where rare classes can have only handfuls of examples. Learning from few examples is a known challenge for deep learning based classification algorithms, and is the focus of the field of low-shot learning. One potential approach to increase the training data for these rare classes is to augment the limited real data with synthetic samples. This has been shown to help, but the domain shift between real and synthetic hinders the approaches' efficacy when tested on real data. We explore the use of image-to-image translation methods to close the domain gap between synthetic and real imagery for animal species classification in data collected from camera traps: motion-activated static cameras used to monitor wildlife. We use low-level feature alignment between source and target domains to make synthetic data for a rare species generated using a graphics engine more "realistic". Compared against a system augmented with unaligned synthetic data, our experiments show a considerable decrease in classification error rates on a rare species.



There are no comments yet.


page 1

page 3

page 4

page 5

page 6


Synthetic Examples Improve Generalization for Rare Classes

The ability to detect and classify rare occurrences in images has import...

Analogical Image Translation for Fog Generation

Image-to-image translation is to map images from a given style to anothe...

One-Shot Image-to-Image Translation via Part-Global Learning with a Multi-adversarial Framework

It is well known that humans can learn and recognize objects effectively...

Scalable learning for bridging the species gap in image-based plant phenotyping

The traditional paradigm of applying deep learning – collect, annotate a...

Improving the Classification of Rare Chords with Unlabeled Data

In this work, we explore techniques to improve performance for rare clas...

TL-SDD: A Transfer Learning-Based Method for Surface Defect Detection with Few Samples

Surface defect detection plays an increasingly important role in manufac...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.