Focus+Context Semantic Representation in Scene Segmentation

被引：0

作者：

Wu L. ^{[1
]}

Zhang X.-Y. ^{[2
]}

Tang M. ^{[2
]}

Wang Z. ^{[3
]}

Wang Y.-A. ^{[4
]}

机构：

[1] Key Laboratory of Broadband Wireless Communication and Sensor Networks, Wuhan University of Technology, Wuhan

[2] School of Resource and Environmental Sciences, Wuhan University, Wuhan

[3] A Unit of the Chinese People's Liberation Army, Wuhan

[4] The 54th Research Institute of China Electronics Technology Group Corporation, Shijiazhuang

来源：

| 1600年 / Chinese Institute of Electronics卷 / 49期

关键词：

Focus+Context; Scene segmentation; Semantic representation; Topic model;

D O I：

10.12263/DZXB.20200161

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Scene segmentation has always been a key and complicated problem in machine learning. In order to understand the scene and recognize the objects more accurately, this paper adopts human attention mechanism, takes the category semantic information into consideration and merges it into the image feature learning. The Focus+Context semantic representation is proposed, where the context describes the relationship between the focus and different objects in the scene, and the focus shared among the same category are composed of similar clusters. The probabilistic topic model is used to compute the local features as well as their semantic information. The experimental results show that the Focus+Context method increases the recognition rate of the scene objects, and specially, the proposed method, in a local and global understanding way, can simplify the scene recognition greatly under a small sample size. © 2021, Chinese Institute of Electronics. All right reserved.

引用

页码：596 / 604

页数：8

共 28 条

[1]

BADUEA C, GUIDOLINIA R, RAPHAEL C, Et al., Self-driving Cars: A Survey

[2]

PORCHERON M, FISCHER J E, REEVES S, Et al., Voice interfaces in everyday life, Proceedings of the CHI Conference on Human Factors in Computing Systems, pp. 1-12, (2018)

[3]

WANG Q, ZHANG L, BERTINETTO L., Fast online object tracking and segmentation: a unifying approach, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1328-1338, (2019)

[4]

TIAN Yan-ling, ZHANG Wei-tong, ZHANG Qie-shi, Et al., Review on image scene classification technology, Acta Electronica Sinica, 47, 4, pp. 915-926, (2019)

[5]

LUO Hui-lan, ZHANG Yun, A survey of image semantic segmentation based on deep network, Acta Electronica Sinica, 47, 10, pp. 2211-2220, (2019)

[6]

HOCK H S, GREGORY P G, WHITEHURST R., Contextual relations: The influence of familiarity, physical plausibility, and belongingness, Attention Perception & Psychophysics, 16, 1, pp. 4-8, (1974)

[7]

QIAN Xiao-liang, BAI Zhen, CHEN Yuan, Et al., A review of co-saliency detection, Acta Electronica Sinica, 47, 6, pp. 1352-1365, (2019)

[8]

LIU T, YUAN Z, SUN J, Et al., Learning to detect a salient object, IEEE Transactions on Pattern Analysis and Machine Intelligence, 33, 2, pp. 353-367, (2011)

[9]

CHEN X W, ZHENG A L, LI J, Et al., Look, perceive and segment: finding the salient objects in images via two-stream fixation semantic CNNs, IEEE International Conference on Computer Vision, pp. 1050-1058, (2017)

[10]

WANG W G, SHEN J B, DONG X P, Et al., Salient object detection driven by fixation prediction, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1711-1720, (2018)

← 1 2 3 →