Delving into the Cyclic Mechanism in Semi-supervised Video Object Segmentation
This addresses segmentation robustness for video analysis applications, representing an incremental improvement over existing pipelines.
The paper tackles error propagation in semi-supervised video object segmentation by incorporating a cyclic mechanism and gradient correction module, achieving improved segmentation quality on DAVIS17 and Youtube-VOS benchmarks.
In this paper, we address several inadequacies of current video object segmentation pipelines. Firstly, a cyclic mechanism is incorporated to the standard semi-supervised process to produce more robust representations. By relying on the accurate reference mask in the starting frame, we show that the error propagation problem can be mitigated. Next, we introduce a simple gradient correction module, which extends the offline pipeline to an online method while maintaining the efficiency of the former. Finally we develop cycle effective receptive field (cycle-ERF) based on gradient correction to provide a new perspective into analyzing object-specific regions of interests. We conduct comprehensive experiments on challenging benchmarks of DAVIS17 and Youtube-VOS, demonstrating that the cyclic mechanism is beneficial to segmentation quality.