InstanceFormer: An Online Video Instance Segmentation Framework

Understand

Recent transformer-based offline video instance segmentation (VIS) approaches achieve encouraging results and significantly outperform online approaches.

• However, their reliance on the whole video and the immense computational complexity caused by full Spatio-temporal attention limit them in real-life applications such as processing lengthy videos.
• In this paper, we propose a single-stage transformer-based efficient online VIS framework named InstanceFormer, which is especially suitable for long and challenging videos.
• We propose three novel components to model short-term and long-term dependency and temporal coherence.