Core Concepts
Hierarchical salience filtering in Salience DETR improves object detection performance by addressing scale bias and redundancy issues.
Stats
DETR-like methods have significantly increased detection performance in an end-to-end manner.
The proposed Salience DETR achieves significant improvements of +4.0% AP, +0.2% AP, +4.4% AP on three challenging task-specific detection datasets, as well as 49.2% AP on COCO 2017 with less FLOPs.
Quotes
"Numerous efforts have been made to mitigate redundant calculation and select discriminative queries."
"We attribute these issues to two types of redundancy in the detection transformer: encoding redundancy and selection redundancy."