返回
CSENet: Cascade semantic erasing network for weakly-supervised semantic segmentation
DOI:10.1016/j.neucom.2020.05.107.png)
摘要
En 中文
Weakly-supervised semantic segmentation based on image-level annotations has difficulty exploring pixel-level information. Most approaches adopt Class Activation Maps (CAM) to localize initial object regions, called seeds. To cover more potential object parts, seeds-expansion methods raise concern for artificial mask generation. Due to the seeds simply focus on discriminative regions, it is a challenge to spread seeds to the integral object. To tackle this problem, we propose a Cascade Semantic Erasing Network (CSENet) to expand seeds effectively and reasonably. In particular, CSENet sequentially stacks the semantic erasing stage to erase discriminative areas progressively. It forces the network to exploit rel-evant feature response for non-discriminative object districts. Moreover, CSENet directly suppresses seeds on the Class Activation Maps (CAM), which have stronger semantics, rather than on the Intermediate Feature Maps (IFM). Under semantic guidance, proposed erasing strategy correctly spreads seeds regions to the intra-class regions and meanwhile, prohibits from extending to the unexpected inter-class areas. Extensive experiments demonstrate the effectiveness of proposed CSENet. More specif-ically, our approach achieves 62.3% and 63.4% mIoU on PASCAL VOC 2012 validation and test set, respectively. (c) 2020 Elsevier B.V. All rights reserved.
Keyword:
Weak supervision
Semantic erasing
Class activation maps
AI总结
对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
暂无机构信息
引用论文
Benchmarking Stability of Iridium Oxide in Acidic Media under Oxygen Evolution Conditions: A Review: Part II酸性介质中铱氧化物在析氧条件下的稳定性基准测试:综述:第二部分
Do Perceptions of Competence Mediate The Relationship Between Fundamental Motor Skill Proficiency and Physical Activity Levels of Children in Kindergarten?能力的感知是否可以介导幼儿园儿童的基本运动技能熟练程度与身体活动水平之间的关系?

