计算机科学
卷积神经网络
人工智能
可视化
视觉对象识别的认知神经科学
代表(政治)
上下文图像分类
对象(语法)
目标检测
语义学(计算机科学)
模式识别(心理学)
深度学习
图像(数学)
程序设计语言
法学
政治
政治学
作者
Bolei Zhou,Àgata Lapedriza,Aditya Khosla,Aude Oliva,Antonio Torralba
标识
DOI:10.1109/tpami.2017.2723009
摘要
The rise of multi-million-item dataset initiatives has enabled data-hungry machine learning algorithms to reach near-human semantic classification performance at tasks such as visual object and scene recognition. Here we describe the Places Database, a repository of 10 million scene photographs, labeled with scene semantic categories, comprising a large and diverse list of the types of environments encountered in the world. Using the state-of-the-art Convolutional Neural Networks (CNNs), we provide scene classification CNNs (Places-CNNs) as baselines, that significantly outperform the previous approaches. Visualization of the CNNs trained on Places shows that object detectors emerge as an intermediate representation of scene classification. With its high-coverage and high-diversity of exemplars, the Places Database along with the Places-CNNs offer a novel resource to guide future progress on scene recognition problems.
科研通智能强力驱动
Strongly Powered by AbleSci AI