Semantic Segmentation from Limited Training Data

TL;DR

This paper introduces two efficient semantic segmentation methods for robotic perception in cluttered scenes with limited training data, successfully applied in the Amazon Robotics Challenge 2017.

Contribution

It presents a deep metric learning approach and a fully-supervised segmentation method that require minimal data and training time, enabling robust perception of unseen categories.

Findings

Few examples suffice to fine-tune deep CNNs for specific segmentation tasks.

Both methods achieved success in the ARC 2017 competition.

Limited data approaches outperform traditional large-data requirements.

Abstract

We present our approach for robotic perception in cluttered scenes that led to winning the recent Amazon Robotics Challenge (ARC) 2017. Next to small objects with shiny and transparent surfaces, the biggest challenge of the 2017 competition was the introduction of unseen categories. In contrast to traditional approaches which require large collections of annotated data and many hours of training, the task here was to obtain a robust perception pipeline with only few minutes of data acquisition and training time. To that end, we present two strategies that we explored. One is a deep metric learning approach that works in three separate steps: semantic-agnostic boundary detection, patch classification and pixel-wise voting. The other is a fully-supervised semantic segmentation approach with efficient dataset collection. We conduct an extensive analysis of the two methods on our ARC 2017 dataset. Interestingly, only few examples of each class are sufficient to fine-tune even very deep convolutional neural networks for this specific task.