Semi-Supervised Video Object Segmentation with Global Feature Enhancement and Mask Correction

To address the issues of low discrimination accuracy of similar objects and error accumulation caused by segmentation errors in video object segmentation, we propose a novel semi-supervised video object segmentation method with global feature enhancement and mask correction. Firstly, we employ a global context-aware module to enhance features by modeling the global dependencies of features via two global memory units, capturing global contextual information within and between video frames and thus improving the models' ability to distinguish between similar distractors. Secondly, we propose a detail-aware decoding which fuses encoded features through skip connections in the early decoding stage to learn detail-enhanced decoding features. Finally, we design a mask correction module at the later decoding stage to estimate uncertain areas in coarse segmentation masks and correct blurred object boundaries and other segmentation errors, producing accurate video object segmentation results. Extensive validation experiments on challenging DAVIS and YouTube-VOS benchmarks demonstrate that our method is significantly better than the compared methods in the paper and outperforms baselines STCN and GSFM on the YouTube-VOS 2019 validation set by 1.6 and 0.3 G, respectively.