Interactive Video Object Segmentation Using Global and Local Transfer Modules

TL;DR

This paper introduces an interactive video object segmentation method that combines deep neural networks with global and local transfer modules, enabling efficient and accurate segmentation with minimal user input.

Contribution

It proposes a novel deep neural network architecture with global and local transfer modules for interactive video segmentation, improving over existing methods.

Findings

Outperforms state-of-the-art algorithms in accuracy

Requires minimal user effort for desired segmentation

Effective bidirectional transfer of segmentation information

Abstract

An interactive video object segmentation algorithm, which takes scribble annotations on query objects as input, is proposed in this paper. We develop a deep neural network, which consists of the annotation network (A-Net) and the transfer network (T-Net). First, given user scribbles on a frame, A-Net yields a segmentation result based on the encoder-decoder architecture. Second, T-Net transfers the segmentation result bidirectionally to the other frames, by employing the global and local transfer modules. The global transfer module conveys the segmentation information in an annotated frame to a target frame, while the local transfer module propagates the segmentation information in a temporally adjacent frame to the target frame. By applying A-Net and T-Net alternately, a user can obtain desired segmentation results with minimal efforts. We train the entire network in two stages, by emulating user scribbles and employing an auxiliary loss. Experimental results demonstrate that the proposed interactive video object segmentation algorithm outperforms the state-of-the-art conventional algorithms. Codes and models are available at https://github.com/yuk6heo/IVOS-ATNet.