Learn Fast, Segment Well: Fast Object Segmentation Learning on the iCub Robot

TL;DR

This paper introduces a fast, incremental object segmentation method for robots that combines pre-trained CNN features with kernel classifiers, enabling quick adaptation to new objects in real-time on the iCub robot.

Contribution

The paper presents a novel pipeline for fast, incremental instance segmentation tailored for robotic applications, integrating pre-trained CNNs with kernel classifiers and a streaming training protocol.

Findings

Effective on robotics datasets

Successfully deployed on iCub robot

Enables online learning of new objects

Abstract

The visual system of a robot has different requirements depending on the application: it may require high accuracy or reliability, be constrained by limited resources or need fast adaptation to dynamically changing environments. In this work, we focus on the instance segmentation task and provide a comprehensive study of different techniques that allow adapting an object segmentation model in presence of novel objects or different domains. We propose a pipeline for fast instance segmentation learning designed for robotic applications where data come in stream. It is based on an hybrid method leveraging on a pre-trained CNN for feature extraction and fast-to-train Kernel-based classifiers. We also propose a training protocol that allows to shorten the training time by performing feature extraction during the data acquisition. We benchmark the proposed pipeline on two robotics datasets and we deploy it on a real robot, i.e. the iCub humanoid. To this aim, we adapt our method to an incremental setting in which novel objects are learned on-line by the robot. The code to reproduce the experiments is publicly available on GitHub.