# Fast User-Guided Video Object Segmentation by Interaction-and-Propagation Networks

## TL;DR

This paper introduces a deep learning approach for interactive video object segmentation that combines interaction and propagation networks, trained jointly to understand user input and produce fast, high-quality segmentation results.

## Contribution

The paper proposes a novel joint training scheme for interaction and propagation networks, enabling effective understanding of user intentions and real-time segmentation updates.

## Key findings

- Outperforms existing methods in speed and accuracy on DAVIS Challenge 2018
- Works effectively with real user interactions
- Runs fast enough for interactive use

## Abstract

We present a deep learning method for the interactive video object segmentation. Our method is built upon two core operations, interaction and propagation, and each operation is conducted by Convolutional Neural Networks. The two networks are connected both internally and externally so that the networks are trained jointly and interact with each other to solve the complex video object segmentation problem. We propose a new multi-round training scheme for the interactive video object segmentation so that the networks can learn how to understand the user's intention and update incorrect estimations during the training. At the testing time, our method produces high-quality results and also runs fast enough to work with users interactively. We evaluated the proposed method quantitatively on the interactive track benchmark at the DAVIS Challenge 2018. We outperformed other competing methods by a significant margin in both the speed and the accuracy. We also demonstrated that our method works well with real user interactions.