Benchmarking SAM2-based Trackers on FMOX
This work provides incremental insights into the performance of existing trackers on specific challenging datasets, aiding researchers in object tracking.
The authors benchmarked several SAM2-based object trackers on datasets with fast-moving objects to assess their limitations, finding that DAM4SAM and SAMURAI performed well on more challenging sequences.
Several object tracking pipelines extending Segment Anything Model 2 (SAM2) have been proposed in the past year, where the approach is to follow and segment the object from a single exemplar template provided by the user on a initialization frame. We propose to benchmark these high performing trackers (SAM2, EfficientTAM, DAM4SAM and SAMURAI) on datasets containing fast moving objects (FMO) specifically designed to be challenging for tracking approaches. The goal is to understand better current limitations in state-of-the-art trackers by providing more detailed insights on the behavior of these trackers. We show that overall the trackers DAM4SAM and SAMURAI perform well on more challenging sequences.