papers AI Learner
The Github is limit! Click to go to the new site.

IvaNet: Learning to jointly detect and segment objets with the help of Local Top-Down Modules


Abstract

Driven by Convolutional Neural Networks, object detection and semantic segmentation have gained significant improvements. However, existing methods on the basis of a full top-down module have limited robustness in handling those two tasks simultaneously. To this end, we present a joint multi-task framework, termed IvaNet. Different from existing methods, our IvaNet backwards abstract semantic information from higher layers to augment lower layers using local top-down modules. The comparisons against some counterparts on the PASCAL VOC and MS COCO datasets demonstrate the functionality of IvaNet.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1903.07360

PDF

http://arxiv.org/pdf/1903.07360


Similar Posts

Comments