Semantic Segmentation from Limited Training Data
This addresses the challenge of rapid deployment in robotics for cluttered scenes with unseen categories, though it is incremental as it adapts existing methods to a specific competition setting.
The authors tackled the problem of semantic segmentation for robotic perception with limited training data, achieving success in the Amazon Robotics Challenge 2017 by using few examples per class to fine-tune deep networks, resulting in robust performance with only minutes of data acquisition and training.
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.