Multi-Source Fusion and Automatic Predictor Selection for Zero-Shot Video Object Segmentation

11 Aug 2021  Â·  Xiaoqi Zhao, Youwei Pang, Jiaxing Yang, Lihe Zhang, Huchuan Lu ·

Location and appearance are the key cues for video object segmentation. Many sources such as RGB, depth, optical flow and static saliency can provide useful information about the objects. However, existing approaches only utilize the RGB or RGB and optical flow. In this paper, we propose a novel multi-source fusion network for zero-shot video object segmentation. With the help of interoceptive spatial attention module (ISAM), spatial importance of each source is highlighted. Furthermore, we design a feature purification module (FPM) to filter the inter-source incompatible features. By the ISAM and FPM, the multi-source features are effectively fused. In addition, we put forward an automatic predictor selection network (APS) to select the better prediction of either the static saliency predictor or the moving object predictor in order to prevent over-reliance on the failed results caused by low-quality optical flow maps. Extensive experiments on three challenging public benchmarks (i.e. DAVIS$_{16}$, Youtube-Objects and FBMS) show that the proposed model achieves compelling performance against the state-of-the-arts. The source code will be publicly available at \textcolor{red}{\url{https://github.com/Xiaoqi-Zhao-DLUT/Multi-Source-APS-ZVOS}}.

PDF Abstract

Datasets


Results from the Paper


 Ranked #1 on Video Object Segmentation on FBMS (Jaccard (Mean) metric)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Video Object Segmentation FBMS ours Jaccard (Mean) 76.7 # 1
Video Object Segmentation YouTube Ours Average 74.9 # 1

Methods