Adaptive token selection for efficient detection transformer with dual teacher supervision

Muyao Yuan, Weizhan Zhang, Caixia Yan, Tieliang Gong, Yuanhong Zhang, Jiangyong Ying

Abstract: Highlights•Methodology for adaptive token selection in DETR based on input difficulty.•An input-aware adaptive training strategy with dual teacher supervision.•A distillation approach to minish the disparities in the feature patterns extracted from adaptive and static model.•Adaptive token selection demonstrates superiority over static token selection methods.