当前位置: X-MOL 学术IEEE Trans. Image Process. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Context-Integrated and Feature-Refined Network for Lightweight Object Parsing
IEEE Transactions on Image Processing ( IF 10.6 ) Pub Date : 2020-03-11 , DOI: 10.1109/tip.2020.2978583
Bin Jiang , Wenxuan Tu , Chao Yang , Junsong Yuan

Semantic segmentation for lightweight object parsing is a very challenging task, because both accuracy and efficiency (e.g., execution speed, memory footprint or computational complexity) should all be taken into account. However, most previous works pay too much attention to one-sided perspective, either accuracy or speed, and ignore others, which poses a great limitation to actual demands of intelligent devices. To tackle this dilemma, we propose a novel lightweight architecture named Context-Integrated and Feature-Refined Network (CIFReNet). The core components of CIFReNet are the Long-skip Refinement Module (LRM) and the Multi-scale Context Integration Module (MCIM). The LRM is designed to ease the propagation of spatial information between low-level and high-level stages. Furthermore, channel attention mechanism is introduced into the process of long-skip learning to boost the quality of low-level feature refinement. Meanwhile, the MCIM consists of three cascaded Dense Semantic Pyramid (DSP) blocks with image-level features, which is presented to encode multiple context information and enlarge the field of view. Specifically, the proposed DSP block exploits a dense feature sampling strategy to enhance the information representations without significantly increasing the computation cost. Comprehensive experiments are conducted on three benchmark datasets for object parsing including Cityscapes, CamVid, and Helen. As indicated, the proposed method reaches a better trade-off between accuracy and efficiency compared with the other state-of-the-art methods.

中文翻译:

用于轻量级对象解析的上下文集成和特征限定的网络

轻量级对象解析的语义分段是一项非常具有挑战性的任务,因为应该同时考虑准确性和效率(例如,执行速度,内存占用量或计算复杂性)。然而,大多数先前的工作都过于注重单方面的观点,无论是准确性还是速度,都忽略了其他方面,这对智能设备的实际需求构成了极大的限制。为了解决这个难题,我们提出了一种新颖的轻量级体系结构,称为“上下文集成的网络和功能指定的网络”(CIFReNet)。CIFReNet的核心组件是长跳过优化模块(LRM)和多尺度上下文集成模块(MCIM)。LRM旨在简化空间信息在底层和高层之间的传播。此外,通道注意机制被引入到长跳过学习的过程中,以提高低级特征细化的质量。同时,MCIM由三个具有图像级特征的级联密集语义金字塔(DSP)块组成,用于对多个上下文信息进行编码并扩大视野。具体而言,提出的DSP模块利用密集特征采样策略来增强信息表示,而不会显着增加计算成本。在用于对象解析的三个基准数据集上进行了全面的实验,包括Cityscapes,CamVid和Helen。如所指出的,与其他现有技术方法相比,所提出的方法在精度和效率之间达到了更好的折衷。同时,MCIM由三个具有图像级特征的级联密集语义金字塔(DSP)块组成,用于对多个上下文信息进行编码并扩大视野。具体而言,提出的DSP模块利用密集特征采样策略来增强信息表示,而不会显着增加计算成本。在用于对象解析的三个基准数据集上进行了全面的实验,包括Cityscapes,CamVid和Helen。如所指出的,与其他现有技术方法相比,所提出的方法在精度和效率之间达到了更好的折衷。同时,MCIM由三个具有图像级特征的级联密集语义金字塔(DSP)块组成,用于对多个上下文信息进行编码并扩大视野。具体而言,提出的DSP模块利用密集特征采样策略来增强信息表示,而不会显着增加计算成本。在用于对象解析的三个基准数据集上进行了全面的实验,包括Cityscapes,CamVid和Helen。如所指出的,与其他现有技术方法相比,所提出的方法在精度和效率之间达到了更好的折衷。提出的DSP模块利用密集特征采样策略来增强信息表示,而不会显着增加计算成本。在用于对象解析的三个基准数据集上进行了全面的实验,包括Cityscapes,CamVid和Helen。如所指出的,与其他现有技术方法相比,所提出的方法在精度和效率之间达到了更好的折衷。提出的DSP模块利用密集特征采样策略来增强信息表示,而不会显着增加计算成本。在用于对象解析的三个基准数据集上进行了全面的实验,包括Cityscapes,CamVid和Helen。如所指出的,与其他现有技术方法相比,所提出的方法在精度和效率之间达到了更好的折衷。
更新日期:2020-04-22
down
wechat
bug