Learning Instance Segmentation by Interaction

TL;DR

This paper introduces a self-supervised approach for an active agent to learn object segmentation through interaction, generalizing to new objects and backgrounds, and demonstrates its utility in a robotic rearrangement task.

Contribution

It presents a novel self-supervised learning method for instance segmentation via interaction, including a robust set loss and a new robotic interaction dataset.

Findings

The model generalizes to novel objects and backgrounds.

The approach achieves effective segmentation with over 50K interactions.

Demonstrated success in a downstream robotic rearrangement task.

Abstract

We present an approach for building an active agent that learns to segment its visual observations into individual objects by interacting with its environment in a completely self-supervised manner. The agent uses its current segmentation model to infer pixels that constitute objects and refines the segmentation model by interacting with these pixels. The model learned from over 50K interactions generalizes to novel objects and backgrounds. To deal with noisy training signal for segmenting objects obtained by self-supervised interactions, we propose robust set loss. A dataset of robot's interactions along-with a few human labeled examples is provided as a benchmark for future research. We test the utility of the learned segmentation model by providing results on a downstream vision-based control task of rearranging multiple objects into target configurations from visual inputs alone. Videos, code, and robotic interaction dataset are available at https://pathak22.github.io/seg-by-interaction/