Feature Selective Networks for Object Detection

Yao Zhai, Jingjing Fu, Yan Lu, Houqiang Li; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 4139-4147

Abstract


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 attention 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 light-weight 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.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Zhai_2018_CVPR,
author = {Zhai, Yao and Fu, Jingjing and Lu, Yan and Li, Houqiang},
title = {Feature Selective Networks for Object Detection},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}
}