DMCA
Learning Deep Features for Scene Recognition using Places Database
Cached
Download Links
| Citations: | 46 - 4 self |
BibTeX
@MISC{Zhou_learningdeep,
author = {Bolei Zhou and Agata Lapedriza and Jianxiong Xiao and Antonio Torralba and Aude Oliva},
title = {Learning Deep Features for Scene Recognition using Places Database},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Scene recognition is one of the hallmark tasks of computer vision, allowing defi-nition of a context for object recognition. Whereas the tremendous recent progress in object recognition tasks is due to the availability of large datasets like ImageNet and the rise of Convolutional Neural Networks (CNNs) for learning high-level fea-tures, performance at scene recognition has not attained the same level of success. This may be because current deep features trained from ImageNet are not competi-tive enough for such tasks. Here, we introduce a new scene-centric database called Places with over 7 million labeled pictures of scenes. We propose new methods to compare the density and diversity of image datasets and show that Places is as dense as other scene datasets and has more diversity. Using CNN, we learn deep features for scene recognition tasks, and establish new state-of-the-art results on several scene-centric datasets. A visualization of the CNN layers ’ responses al-lows us to show differences in the internal representations of object-centric and scene-centric networks. 1
Keyphrases
scene recognition deep feature place database new method convolutional neural network labeled picture several scene-centric datasets high-level fea-tures scene recognition task new scene-centric database computer vision large datasets current deep feature cnn layer object recognition task new state-of-the-art result hallmark task internal representation scene-centric network object recognition image datasets scene datasets tremendous recent progress
