Spatiotemporal CNN for Video Object Segmentation

TL;DR

This paper introduces a unified spatiotemporal CNN model for video object segmentation that leverages adversarial training and a coarse-to-fine attention mechanism to improve segmentation accuracy on challenging datasets.

Contribution

The novel end-to-end trainable model combines a temporal coherence branch with a spatial segmentation branch, utilizing adversarial pretraining and multi-scale attention for enhanced VOS performance.

Findings

Achieves state-of-the-art results on DAVIS and Youtube-Object datasets.

Effectively captures dynamic appearance and motion cues.

Improves segmentation accuracy with a coarse-to-fine attention approach.

Abstract

In this paper, we present a unified, end-to-end trainable spatiotemporal CNN model for VOS, which consists of two branches, i.e., the temporal coherence branch and the spatial segmentation branch. Specifically, the temporal coherence branch pretrained in an adversarial fashion from unlabeled video data, is designed to capture the dynamic appearance and motion cues of video sequences to guide object segmentation. The spatial segmentation branch focuses on segmenting objects accurately based on the learned appearance and motion cues. To obtain accurate segmentation results, we design a coarse-to-fine process to sequentially apply a designed attention module on multi-scale feature maps, and concatenate them to produce the final prediction. In this way, the spatial segmentation branch is enforced to gradually concentrate on object regions. These two branches are jointly fine-tuned on video segmentation sequences in an end-to-end manner. Several experiments are carried out on three challenging datasets (i.e., DAVIS-2016, DAVIS-2017 and Youtube-Object) to show that our method achieves favorable performance against the state-of-the-arts. Code is available at https://github.com/longyin880815/STCNN.