Places: An Image Database for Deep Scene Understanding

TL;DR

The paper introduces the Places Database, a large-scale image repository with diverse scene categories, enabling advances in scene understanding through deep learning models.

Contribution

It presents a comprehensive, labeled dataset of 10 million images for scene recognition, facilitating progress in deep scene understanding.

Findings

High baseline performance in scene classification using CNNs

Diverse and extensive dataset supports complex visual recognition tasks

Enables future research in intractable visual recognition problems

Abstract

The rise of multi-million-item dataset initiatives has enabled data-hungry machine learning algorithms to reach near-human semantic classification at tasks such as object and scene recognition. Here we describe the Places Database, a repository of 10 million scene photographs, labeled with scene semantic categories and attributes, comprising a quasi-exhaustive list of the types of environments encountered in the world. Using state of the art Convolutional Neural Networks, we provide impressive baseline performances at scene classification. With its high-coverage and high-diversity of exemplars, the Places Database offers an ecosystem to guide future progress on currently intractable visual recognition problems.