#54
summarized by : Anonymous
QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection
Chenhongyi Yang; Zehao Huang; Naiyan Wang

どんな論文か？

effectively detecting small objects using high-resolution feature maps (e.g., P2 in FPN) for feature pyramid-based object detectors by Cascade Sparse Query (CSQ); CSQ reduces computation cost
placeholder

新規性

making predictions only on locations potentially containing small objects (Sparse Query, identified by small object existence prediction on coarse feature maps) on high-resolution feature maps

結果

better performance obtained compared with RetinaNet and FOCS on COCO, VisDrone

その他（なぜ通ったか？等）

training of classification and regression branches is kept the same as in the original RetinaNet; a query head for small object prediction (classification task, not regression) is added

このページで利用されている画像は論文から引用しています．