Iteratively Trained Interactive Segmentation

TL;DR

This paper introduces an iterative training approach for interactive object segmentation that improves accuracy by dynamically adding user clicks during training, leading to better performance than existing methods.

Contribution

It proposes a novel iterative training strategy for interactive segmentation that enhances model performance over prior heuristic-based approaches.

Findings

Achieves improved segmentation accuracy over state-of-the-art methods.

Demonstrates effectiveness of iterative click addition during training.

Enhances network architecture for better segmentation results.

Abstract

Deep learning requires large amounts of training data to be effective. For the task of object segmentation, manually labeling data is very expensive, and hence interactive methods are needed. Following recent approaches, we develop an interactive object segmentation system which uses user input in the form of clicks as the input to a convolutional network. While previous methods use heuristic click sampling strategies to emulate user clicks during training, we propose a new iterative training strategy. During training, we iteratively add clicks based on the errors of the currently predicted segmentation. We show that our iterative training strategy together with additional improvements to the network architecture results in improved results over the state-of-the-art.