Single-Shot Object Detection with Enriched Semantics
Name
CBMM-Memo-084.pdf
Size
1.92 MB
Format
Adobe PDF
Checksum (MD5)
6b903b6baf81fdb5610b9a16c7a17f00
Author(s)
Zhang, Zhishuai
Qiao, Siyuan
Xie, Cihang
Shen, Wei
Wang, Bo
Yuille, Alan L.
Date Issued
June 19, 2018
Publisher
Center for Brains, Minds and Machines (CBMM)
Series/Report no.
CBMM Memo Series;084
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.
Persistent DSpace Link
