BshapeNet: Object detection and instance segmentation with bounding shape masks

Kang, Ba Rom

doi:10.1016/j.patrec.2020.01.024

BshapeNet: Object detection and instance segmentation with bounding shape masks

2020-03-01

23

OA

AI

DOI：10.1016/j.patrec.2020.01.024

原文链接

查看原文

摘要

En 中文

We propose a modularizable component that can predict the boundary shapes and boxes of an image, along with a new masking scheme for improving object detection and instance segmentation. Specifically, we introduce two types of novel masks: a bounding box (bbox) mask and a bounding shape (bshape) mask. For each of these types, we consider two variants-the Thick model and the Scored model-both of which have the same morphology but differ in ways that make their boundaries thicker. To evaluate our masks, we design extended frameworks by adding a bshape mask (or a bbox mask) branch to a Faster R-CNN, and call this BshapeNet (or BboxNet). Furthermore, we propose BshapeNet+, a network that combines a bshape mask branch with a Mask R-CNN. Among our various models, BshapeNet+ demonstrates the best performance in both tasks. In addition, BshapeNet+ markedly outperforms the baseline models on MS COCO and Cityscapes and achieves highly competitive results with state-of-the-art models. In particular, the experimental results show that our branch works well on small objects and is easily applicable to various models, such as PANet as well as Faster R-CNN and Mask R-CNN. (C) 2020 Elsevier B.V. All rights reserved.

BshapeNet: Object detection and instance segmentation with bounding shape masks

摘要

AI总结

期刊

机构

引用论文