Places: A 10 Million Image Database for Scene Recognition
Citations Over TimeTop 1% of 2017 papers
Abstract
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.
Related Papers
- → Comparison of the NCI Open Database with Seven Large Chemical Structural Databases(2001)217 cited
- → The importance of population-specific normal database for quantification of myocardial ischemia: comparison between Japanese 360 and 180-degree databases and a US database(2009)59 cited
- → Safety Signals Using Proportional Reporting Ratios from Company and Regulatory Authority Databases(2008)4 cited
- → Drug information through online databases : a comparison between external databases and the in-house database of a pharmaceutical company(1991)1 cited
- Commercial Databases : The Keypoints and Practical Use(1) - Trends of Database Services -(1993)