Flow-guided Semi-supervised Video Object Segmentation

TL;DR

This paper introduces a novel optical flow-guided semi-supervised video object segmentation method that uses an attention mechanism to effectively integrate flow and image data, achieving state-of-the-art results.

Contribution

It proposes a new attention-based approach to combine optical flow with image data for improved semi-supervised video segmentation.

Findings

Achieves state-of-the-art performance on DAVIS 2017.

Integrating optical flow significantly improves segmentation accuracy.

The attention mechanism outperforms simple concatenation methods.

Abstract

We propose an optical flow-guided approach for semi-supervised video object segmentation. Optical flow is usually exploited as additional guidance information in unsupervised video object segmentation. However, its relevance in semi-supervised video object segmentation has not been fully explored. In this work, we follow an encoder-decoder approach to address the segmentation task. A model to extract the combined information from optical flow and the image is proposed, which is then used as input to the target model and the decoder network. Unlike previous methods where concatenation is used to integrate information from image data and optical flow, a simple yet effective attention mechanism is exploited in our work. Experiments on DAVIS 2017 and YouTube-VOS 2019 show that by integrating the information extracted from optical flow into the original image branch results in a strong performance gain and our method achieves state-of-the-art performance.