arrow
返回

Scene Recognition With Prototype-Agnostic Scene Layout

delete2020-01-01
delete46
delete
OA
AI
G
Gongwei Chen
宋新航 (Xinhang Song)
H
Haitao Zeng
S
Shuqiang Jiang *
DOI:10.1109/TIP.2020.2986599delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
Exploiting the spatial structure in scene images is a key research direction for scene recognition. Due to the large intra-class structural diversity, building and modeling flexible structural layout to adapt various image characteristics is a challenge. Existing structural modeling methods in scene recognition either focus on predefined grids or rely on learned prototypes, which all have limited representative ability. In this paper, we propose Prototype-agnostic Scene Layout (PaSL) construction method to build the spatial structure for each image without conforming to any prototype. Our PaSL can flexibly capture the diverse spatial characteristic of scene images and have considerable generalization capability. Given a PaSL, we build Layout Graph Network (LGN) where regions in PaSL are defined as nodes and two kinds of independent relations between regions are encoded as edges. The LGN aims to incorporate two topological structures (formed in spatial and semantic similarity dimensions) into image representations through graph convolution. Extensive experiments show that our approach achieves state-of-the-art results on widely recognized MIT67 and SUN397 datasets without multi-model or multi-scale fusion. Moreover, we also conduct the experiments on one of the largest scale datasets, Places365. The results demonstrate the proposed method can be well generalized and obtains competitive performance.
Keyword:
Layout
Semantics
Prototypes
Image recognition
Convolution
Neural networks
Deformable models
Scene classification
convolution neural networks
graph neural networks
scene layout
AI总结

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

IEEE Transactions on Image Processing 封面图
IEEE Transactions on Image Processing
IF:
13.7
论文数:
1.0W
被引数:
8.4W

机构

I
institute of computing technology, cas
学者数:
1.0K
论文数: 877
被引数: 1
C
chinese academy of sciences
学者数:
56.7W
论文数: 45.0W
被引数: 704
引用论文

引用论文

Ingestion of corrosive acids
err1989-09-01
err0
PREAI
errShowkat Ali Zargar; Rakesh Kochhar; Birender Nagi; Saroj Mehta; Satish Kumar Mehta
err分享
err收藏
QuantumNAS: Noise-Adaptive Search for Robust Quantum Circuits
err2022-04-01
err0
errOAAI
errHanrui Wang; Yongshan Ding; Jiaqi Gu; Yujun Lin; David Z. Pan; Frederic T. Chong; Song Han
err分享
err收藏
Vitamin D and Its Role in Ulcerative Colitis
err2015-11-01
err0
PREAI
errEhsan Shahverdi; Mohammad Amin Konjedi; Ashkan Shahverdi; Amin Dehghanian; Hossein Khedmat
err分享
err收藏
Systematic review of surveillance systems and methods for early detection of exotic, new and re-emerging diseases in animal populations
err2014-09-12
err0
errOAAI
errV. RODRÍGUEZ-PRIETO; M. VICENTE-RUBIANO; A. SÁNCHEZ-MATAMOROS; C. RUBIO-GUERRI; M. MELERO; B. MARTÍNEZ-LÓPEZ; M. MARTÍNEZ-AVILÉS; L. HOINVILLE; T. VERGNE; A. COMIN; B. SCHAUER; F. DÓREA; D. U. PFEIFFER; J. M. SÁNCHEZ-VIZCAÍNO
err分享
err收藏
学者 查看更多内容