The authors propose a weakly supervised self-training approach to adapt the pre-trained Segment-Anything (SAM) model to diverse downstream segmentation tasks, overcoming the generalization issues of SAM under significant distribution shift.
The authors propose a novel mixed query strategy that can effectively and dynamically accommodate different types of objects without heuristic designs, enabling a unified architecture for multi-task and multi-dataset image segmentation using a single set of weights.
提案されたアプローチは、インタラクティブ画像セグメンテーションにおいて、革新的な方法を導入し、最先端のパフォーマンスを達成することができる。
PEM introduces an efficient transformer-based architecture for image segmentation tasks, showcasing outstanding performance and efficiency.