Collaborative Attention Memory Network for Video Object Segmentation
This work addresses a fundamental computer vision task for video analysis, but it is incremental as it builds on existing CFBI and STM networks.
The paper tackles semi-supervised video object segmentation by addressing false predictions from limited first-frame appearance and issues like occlusion, proposing a Collaborative Attention Memory Network with an enhanced segmentation head and ensemble approach. It achieved 6th place in the 2021 YouTube-VOS challenge with an overall score of 83.5%.
Semi-supervised video object segmentation is a fundamental yet Challenging task in computer vision. Embedding matching based CFBI series networks have achieved promising results by foreground-background integration approach. Despite its superior performance, these works exhibit distinct shortcomings, especially the false predictions caused by little appearance instances in first frame, even they could easily be recognized by previous frame. Moreover, they suffer from object's occlusion and error drifts. In order to overcome the shortcomings , we propose Collaborative Attention Memory Network with an enhanced segmentation head. We introduce a object context scheme that explicitly enhances the object information, which aims at only gathering the pixels that belong to the same category as a given pixel as its context. Additionally, a segmentation head with Feature Pyramid Attention(FPA) module is adopted to perform spatial pyramid attention structure on high-level output. Furthermore, we propose an ensemble network to combine STM network with all these new refined CFBI network. Finally, we evaluated our approach on the 2021 Youtube-VOS challenge where we obtain 6th place with an overall score of 83.5\%.