DeepFH segmentations for superpixel-based object proposal refinement

Christian Wilms

doi:10.1016/j.imavis.2021.104263

Return

DeepFH segmentations for superpixel-based object proposal refinement

2021-10-01

Christian Wilms *

Simone Frintrop

DOI：10.1016/j.imavis.2021.104263

Original

Save

View PDF

Abstract

En 中文

Class-agnostic object proposal generation is an important first step in many object detection pipelines. However, object proposals of modern systems are rather inaccurate in terms of segmentation and only roughly adhere to object boundaries. Since typical refinement steps are usually not applicable to thousands of proposals, we pro -pose a superpixel-based refinement system for object proposal generation systems. Utilizing precise superpixels and superpixel pooling on deep features, we refine initial coarse proposals in an end-to-end learned system. Fur-thermore, we propose a novel DeepFH segmentation, which enriches the classic Felzenszwalb and Huttenlocher (FH) segmentation with deep features leading to improved segmentation results and better object proposal re-finements. On the COCO dataset with LVIS annotations, we show that our refinement based on DeepFH superpixels outperforms state-of-the-art methods and leads to more precise object proposals. (c) 2021 Elsevier B.V. All rights reserved.

Keywords:

Object proposals

Image segmentation

Superpixels

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.