Feature Selective Networks for Object Detection

Yao Zhai, Jingjing Fu, Yan Lu, Houqiang Li
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
Objects for detection usually have distinct characteristics in different sub-regions and different aspect ratios. However, in prevalent two-stage object detection methods, Region-of-Interest (RoI) features are extracted by RoI pooling with little emphasis on these translation-variant feature components. We present feature selective networks to reform the feature representations of RoIs by exploiting their disparities among sub-regions and aspect ratios. Our network produces the sub-region
more » ... ion bank and aspect ratio attention bank for the whole image. The RoI-based sub-region attention map and aspect ratio attention map are selectively pooled from the banks, and then used to refine the original RoI features for RoI classification. Equipped with a lightweight detection subnetwork, our network gets a consistent boost in detection performance based on general ConvNet backbones (ResNet-101, GoogLeNet and VGG-16). Without bells and whistles, our detectors equipped with ResNet-101 achieve more than 3% mAP improvement compared to counterparts on PASCAL VOC 2007, PASCAL VOC 2012 and MS COCO datasets. * This work was done during an internship at Microsoft Research Asia.
doi:10.1109/cvpr.2018.00435 dblp:conf/cvpr/ZhaiF0L18 fatcat:7xtlg57kzrd23pkbzhwhfsfuxy