Single-Shot Object Detection with Enriched Semantics

TitleSingle-Shot Object Detection with Enriched Semantics
Publication TypeConference Paper
Year of PublicationIn Press
AuthorsZhang, Z, Qiao, S, Xie, C, Shen, W, Wang, B, Yuille, A
Conference NameConference on Computer Vision and Pattern Recognition (CVPR)
Date Published06/2018
Conference LocationSalt Lake City, Utah

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.


Research Area: 

CBMM Relationship: 

  • CBMM Funded