|Title||Single-Shot Object Detection with Enriched Semantics|
|Publication Type||Conference Paper|
|Year of Publication||2018|
|Authors||Zhang, Z, Qiao, S, Xie, C, Shen, W, Wang, B, Yuille, A|
|Conference Name||Conference on Computer Vision and Pattern Recognition (CVPR)|
|Conference Location||Salt 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.
- CBMM Funded