arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.13665cs.CV
收藏

一种新的用于实例分割的感兴趣区域提取层

A novel Region of Interest Extraction Layer for Instance Segmentation

University of Parma(帕尔马大学)

Leonardo Rossi, Akbar Karimi, Andrea Prati

摘要:

鉴于用于计算机视觉任务的深度神经网络架构的广泛传播,一些新的应用现在越来越可行。其中,最近特别关注的是实例分割,通过利用从R-CNN导出的两阶段网络(如Mask R-CNN或Faster R-CNN)可实现的结果。在这些复杂的体系结构中,感兴趣区域(ROI)提取层扮演着至关重要的角色,该层致力于从连接在主干之上的单个特征金字塔网络(FPN)层中提取一致的特征子集。本文的动机是需要克服现有的ROI提取器,只选择一个(最好的)层从FPN的局限性。我们的直觉是,FPN的所有层都保留了有用的信息。因此,所提出的层(称为通用RoI提取器- GRoIE)引入非本地构建块和注意力机制来提高性能。在组件级进行全面的消融研究,以找到GRoIE层的最佳算法和参数集。此外,GRoIE可以无缝地集成到每个两阶段的体系结构,用于目标检测和实例分割任务。因此,在不同的国家的最先进的架构中使用GRoIE所带来的改进也进行了评估。提出的层导致获得1.1%的AP提高限界框检测和1.7%的AP提高实例分割。该代码在GitHub存储库https://github.com/IMPLabUniPr/mmdetection/tree/groie_dev上公开提供

英文摘要:

Given the wide diffusion of deep neural network architectures for computer vision tasks, several new applications are nowadays more and more feasible. Among them, a particular attention has been recently given to instance segmentation, by exploiting the results achievable by two-stage networks (such as Mask R-CNN or Faster R-CNN), derived from R-CNN. In these complex architectures, a crucial role is played by the Region of Interest (RoI) extraction layer, devoted to extracting a coherent subset of features from a single Feature Pyramid Network (FPN) layer attached on top of a backbone. This paper is motivated by the need to overcome the limitations of existing RoI extractors which select only one (the best) layer from FPN. Our intuition is that all the layers of FPN retain useful information. Therefore, the proposed layer (called Generic RoI Extractor - GRoIE) introduces non-local building blocks and attention mechanisms to boost the performance. A comprehensive ablation study at component level is conducted to find the best set of algorithms and parameters for the GRoIE layer. Moreover, GRoIE can be integrated seamlessly with every two-stage architecture for both object detection and instance segmentation tasks. Therefore, the improvements brought about by the use of GRoIE in different state-of-the-art architectures are also evaluated. The proposed layer leads up to gain a 1.1% AP improvement on bounding box detection and 1.7% AP improvement on instance segmentation. The code is publicly available on GitHub repository at https://github.com/IMPLabUniPr/mmdetection/tree/groie_dev

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑