Abstract
With the development of deep convolutional neural network, the performance of object detection is obviously improved. However, there are still some challenges such as small size and occlusion. In this paper, we present a novel detector named Attention Mask Detector (AMDet). Our motivation is using mask to enhance foreground features and suppress background ones. The mask is produced by an attention branch which is supervised by weak segmentation ground-truth. This weak segmentation ground-truth is generated by bounding box without extra annotations. Our method is based on one-stage detector. We do experiments on both PASCAL VOC and MS COCO datasets and have a result comparison with other one-stage detectors.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
