Interactive Segmentation for Diverse Gesture Types Without Context

TL;DR

This paper introduces a new interactive segmentation task supporting multiple gesture types without requiring users to specify gesture types, along with a novel dataset and evaluation metric for comprehensive assessment.

Contribution

It presents the first dataset and evaluation metric for multi-gesture interactive segmentation, enabling more flexible user interactions without gesture type specification.

Findings

Supported multiple gesture types in segmentation algorithms

Analyzed performance of existing algorithms on new task

Identified areas for future improvement

Abstract

Interactive segmentation entails a human marking an image to guide how a model either creates or edits a segmentation. Our work addresses limitations of existing methods: they either only support one gesture type for marking an image (e.g., either clicks or scribbles) or require knowledge of the gesture type being employed, and require specifying whether marked regions should be included versus excluded in the final segmentation. We instead propose a simplified interactive segmentation task where a user only must mark an image, where the input can be of any gesture type without specifying the gesture type. We support this new task by introducing the first interactive segmentation dataset with multiple gesture types as well as a new evaluation metric capable of holistically evaluating interactive segmentation algorithms. We then analyze numerous interactive segmentation algorithms, including ones adapted for our novel task. While we observe promising performance overall, we also highlight areas for future improvement. To facilitate further extensions of this work, we publicly share our new dataset at https://github.com/joshmyersdean/dig.