Corpus ID: 1849990

Learning Deep Features for Scene Recognition using Places Database

@inproceedings{Zhou2014LearningDF,
  title={Learning Deep Features for Scene Recognition using Places Database},
  author={Bolei Zhou and {\`A}. Lapedriza and J. Xiao and A. Torralba and A. Oliva},
  booktitle={NIPS},
  year={2014}
}
Scene recognition is one of the hallmark tasks of computer vision, allowing definition of a context for object recognition. [...] Key Method 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 allows us to show differences…Expand
Places: A 10 Million Image Database for Scene Recognition
TLDR
The Places Database is described, 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 as baselines, that significantly outperform the previous approaches. Expand
Scene Classification with Deep Convolutional Neural Networks
TLDR
This project proposed a novel scene classification method which combines CNN and Spatial Pyramid to generate high-level contextaware features for one-vs-all linear SVMs and achieves better average accuracy rate than any other state-of-the-art result on MIT indoor67 dataset using only the deep features trained from ImageNet. Expand
Learning Scene Attribute for Scene Recognition
TLDR
This paper discusses the discrimination of scene attributes in local regions and utilize scene attributes as the complementary features of object and scene features and aggregate these features and generate more discriminative scene representations, which achieve better performance than the feature aggregation ofobject and scene. Expand
Scene Categorization Through Using Objects Represented by Deep Features
  • Shuang Bai
  • Computer Science
  • Int. J. Pattern Recognit. Artif. Intell.
  • 2017
TLDR
This approach combines benefits of deep learning and Latent Support Vector Machine to train a set of scene-specific object models for each scene category, which are obtained by alternating between searching over the most representative and discriminative regions of images in the target dataset and training linear SVM classifiers based on obtained region features. Expand
Object Detectors Emerge from Training CNNs for Scene Recognition
With the success of new computational architectures for visual processing, such as convolutional neural networks (CNN) and access to image databases with millions of labeled examples (e.g., ImageNet,Expand
Multi-Scale Convolutional Neural Networks for Scene Recognition
  • Zheng Yi, Han-ling Zhang
  • Computer Science
  • 2019 IEEE 21st International Conference on High Performance Computing and Communications; IEEE 17th International Conference on Smart City; IEEE 5th International Conference on Data Science and Systems (HPCC/SmartCity/DSS)
  • 2019
TLDR
A method of feature fusion at the level of category, aiming to effectively combine different scale features at multiple levels, and shows that the success of the object classification task can be applied to the scene recognition task by this method. Expand
Semantic-Aware Scene Recognition
TLDR
A novel approach for scene recognition based on an end-to-end multi-modal CNN that combines image and context information by means of an attention module is described, which outperforms every other state-of-the-art method while significantly reducing the number of network parameters. Expand
Multi-Level Ensemble Network for Scene Recognition
TLDR
Multi-Level Ensemble Network (MLEN), a convolutional neural network, has been proposed, to improve the recognition accuracy of these “small object-supported scenes” and a class-weight loss function for the problem of non-uniform class distribution has been designed. Expand
Using Deep Convolutional Neural Network in Computer Vision for Real-World Scene Classification
TLDR
Object classification task has drastically improved by using the Deep Learning, Alex Net Convolutional Neural Network for extracting the features of input image automatically and then applying the transfer learning approach for classification task to reduce the overall computational complexity of the neural network. Expand
Understand scene categories by objects: A semantic regularized scene classifier using Convolutional Neural Networks
TLDR
The proposed deep architecture achieves superior scene classification results to the state-of-the-art on a publicly available SUN RGB-D dataset, and performance of semantic segmentation, the regularizer, reaches a new record with refinement derived from predicted scene labels. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 29 REFERENCES
CNN Features Off-the-Shelf: An Astounding Baseline for Recognition
TLDR
A series of experiments conducted for different recognition tasks using the publicly available code and model of the OverFeat network which was trained to perform object classification on ILSVRC13 suggest that features obtained from deep learning with convolutional nets should be the primary candidate in most visual recognition tasks. Expand
DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
TLDR
DeCAF, an open-source implementation of deep convolutional activation features, along with all associated network parameters, are released to enable vision researchers to be able to conduct experimentation with deep representations across a range of visual concept learning paradigms. Expand
SUN database: Large-scale scene recognition from abbey to zoo
TLDR
This paper proposes the extensive Scene UNderstanding (SUN) database that contains 899 categories and 130,519 images and uses 397 well-sampled categories to evaluate numerous state-of-the-art algorithms for scene recognition and establish new bounds of performance. Expand
ImageNet classification with deep convolutional neural networks
TLDR
A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective. Expand
Recognizing indoor scenes
TLDR
A prototype based model that can successfully combine local and global discriminative information is proposed that can significantly outperform a state of the art classifier for the indoor scene recognition task. Expand
Analyzing the Performance of Multilayer Neural Networks for Object Recognition
TLDR
This paper experimentally probes several aspects of CNN feature learning in an attempt to help practitioners gain useful, evidence-backed intuitions about how to apply CNNs to computer vision problems. Expand
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
  • S. Lazebnik, C. Schmid, J. Ponce
  • Computer Science
  • 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
  • 2006
TLDR
This paper presents a method for recognizing scene categories based on approximate global geometric correspondence that exceeds the state of the art on the Caltech-101 database and achieves high accuracy on a large database of fifteen natural scene categories. Expand
Unbiased look at dataset bias
TLDR
A comparison study using a set of popular datasets, evaluated based on a number of criteria including: relative data bias, cross-dataset generalization, effects of closed-world assumption, and sample value is presented. Expand
Caltech-256 Object Category Dataset
We introduce a challenging set of 256 object categories containing a total of 30607 images. The original Caltech-101 [1] was collected by choosing a set of object categories, downloading examplesExpand
What, where and who? Classifying events by scene and object recognition
  • Li-Jia Li, Li Fei-Fei
  • Computer Science
  • 2007 IEEE 11th International Conference on Computer Vision
  • 2007
TLDR
This paper uses a number of sport games such as snow boarding, rock climbing or badminton to demonstrate event classification and proposes a first attempt to classify events in static images by integrating scene and object categorizations. Expand
...
1
2
3
...