@conference {3549, title = {Single-Shot Object Detection with Enriched Semantics}, booktitle = {Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2018}, month = {06/2018}, address = {Salt Lake City, Utah}, abstract = {

We propose a novel single shot object detection network named Detection with Enriched Semantics (DES). Our motivation is to enrich the semantics of object detection features within a typical deep detector, by a semantic segmentation branch and a global activation module. The segmentation branch is supervised by weak segmentation ground-truth, i.e., no extra annotation is required. In conjunction with that, we employ a global activation module which learns relationship between channels and object classes in a self-supervised manner. Comprehensive experimental results on both PASCAL VOC and MS COCO detection datasets demonstrate the effectiveness of the proposed method. In particular, with a VGG16 based DES, we achieve an mAP of 81.7 on VOC2007 test and an mAP of 32.8 on COCO test-dev with an inference speed of 31.5 milliseconds per image on a Titan Xp GPU. With a lower resolution version, we achieve an mAP of 79.7 on VOC2007 with an inference speed of 13.0 milliseconds per image.

}, url = {http://cvpr2018.thecvf.com/}, author = {Zhishuai Zhang and Siyuan Qiao and Cihang Xie and Wei Shen and Bo Wang and Alan Yuille} }