Online citations, reference lists, and bibliographies.

Growing Random Forest On Deep Convolutional Neural Networks For Scene Categorization

Shuang Bai
Published 2017 · Computer Science
Cite This
Download PDF
Analyze on Scholarcy
Share
Random forests are grown on convolutional neural networks for scene categorization.Features from multi-layers of deep convolutional neural networks are utilized.A feature selection method is proposed to use random forests to categorize scenes. Breakthrough performances have been achieved in computer vision by utilizing deep neural networks. In this paper we propose to use random forest to classify image representations obtained by concatenating multiple layers of learned features of deep convolutional neural networks for scene classification. Specifically, we first use deep convolutional neural networks pre-trained on the large-scale image database Places to extract features from scene images. Then, we concatenate multiple layers of features of the deep neural networks as image representations. After that, we use random forest as the classifier for scene classification. Moreover, to reduce feature redundancy in image representations we derived a novel feature selection method for selecting features that are suitable for random forest classification. Extensive experiments are conducted on two benchmark datasets, i.e. MIT-Indoor and UIUC-Sports. Obtained results demonstrated the effectiveness of the proposed method. The contributions of the paper are as follows. First, by extracting multiple layers of deep neural networks, we can explore more information of image contents for determining their categories. Second, we proposed a novel feature selection method that can be used to reduce redundancy in features obtained by deep neural networks for classification based on random forest. In particular, since deep learning methods can be used to augment expert systems by having the systems essentially training themselves, and the proposed framework is general, which can be easily extended to other intelligent systems that utilize deep learning methods, the proposed method provide a potential way for improving performances of other expert and intelligent systems.
This paper references
Mid-level Visual Element Discovery as Discriminative Mode Seeking
Carl Doersch (2013)
10.1109/CVPR.2015.7298594
Going deeper with convolutions
Christian Szegedy (2015)
10.1007/978-1-84882-491-1
Natural Image Statistics - A Probabilistic Approach to Early Computational Vision
Aapo Hyvärinen (2009)
10.1109/ICCV.2007.4408872
What, where and who? Classifying events by scene and object recognition
Li-Jia Li (2007)
10.1561/2200000006
Learning Deep Architectures for AI
Yoshua Bengio (2007)
10.1109/CVPR.2010.5539963
Learning mid-level features for recognition
Y-Lan Boureau (2010)
Caffe : An open source convolutional architecture for fast feature embedding
Y. Jia (2013)
10.1109/CVPR.2010.5540018
Locality-constrained Linear Coding for image classification
Jinjun Wang (2010)
10.1109/TPAMI.2012.231
Learning Hierarchical Features for Scene Labeling
Clément Farabet (2013)
10.1109/TNNLS.2014.2307532
Learning Deep Hierarchical Visual Feature Coding
Hanlin Goh (2014)
10.1109/CVPR.2013.368
Supervised Kernel Descriptors for Visual Recognition
Peng Wang (2013)
10.1109/CVPRW.2009.5206848
ImageNet: A large-scale hierarchical image database
Jia Deng (2009)
10.1109/TPAMI.2010.224
CENTRIST: A Visual Descriptor for Scene Categorization
Jianxin Wu (2011)
10.1016/j.eswa.2014.11.069
Scene classification based on single-layer SAE and SVM
Hongpeng Yin (2015)
10.1109/CVPR.2014.37
Incorporating Scene Context and Object Layout into Appearance Modeling
Hamid Izadinia (2014)
10.17148/IJARCCE.2019.8443
Semantic Texton Forests for Image Categorization and Segmentation
Miss Nilophar Mullani (2019)
10.1016/j.eswa.2014.07.042
Indoor localization in a hospital environment using Random Forest classifiers
Luca Calderoni (2015)
10.1145/3065386
ImageNet classification with deep convolutional neural networks
Alex Krizhevsky (2017)
10.1109/CVPR.2009.5206537
Recognizing indoor scenes
Ariadna Quattoni (2009)
10.1109/CAIVD.1998.646032
Indoor-outdoor image classification
Martin Szummer (1998)
10.1016/j.eswa.2015.02.001
Risk assessment in social lending via random forests
Milad Malekipirbazari (2015)
10.1061/(ASCE)GT.1943-5606.0001284
ImageNet Classification with Deep Convolutional Neural Networks
Alex Krizhevsky (2012)
10.1007/978-3-540-88690-7_52
Kernel Codebooks for Scene Categorization
Jan C. van Gemert (2008)
Object Detectors Emerge in Deep Scene CNNs
Bolei Zhou (2015)
10.1007/978-3-642-33715-4_17
Latent Pyramidal Regions for Recognizing Scenes
Fereshteh Sadeghi (2012)
10.1109/CVPR.2006.68
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
Svetlana Lazebnik (2006)
10.1023/A:1011139631724
Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope
Aude Oliva (2001)
10.1109/CVPR.2013.124
Blocks That Shout: Distinctive Parts for Scene Classification
Mayank Juneja (2013)
10.1109/TPAMI.2007.70822
Randomized Clustering Forests for Image Classification
Frank Moosmann (2008)
10.1109/34.895972
Content-Based Image Retrieval at the End of the Early Years
Arnold W. M. Smeulders (2000)
10.1109/ICCV.2011.6126383
Scene recognition and weakly supervised object localization with deformable part-based models
Megha Pandey (2011)
10.1109/ICCV.2007.4409066
Image Classification using Random Forests and Ferns
Anna Bosch (2007)
DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
Jeff Donahue (2014)
10.1007/978-3-642-33709-3_6
Unsupervised Discovery of Mid-Level Discriminative Patches
Saurabh Singh (2012)
10.1016/j.eswa.2011.03.037
Region Contextual Visual Words for scene categorization
Shuoyan Liu (2011)
Learning Deep Features for Scene Recognition using Places Database
Bolei Zhou (2014)
10.1109/CVPRW.2014.131
CNN Features Off-the-Shelf: An Astounding Baseline for Recognition
Ali Sharif Razavian (2014)
10.1016/j.eswa.2013.02.002
A low-cost INS/GPS integration methodology based on random forest regression
Srujana Adusumilli (2013)
10.1109/CVPR.2014.81
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Ross B. Girshick (2014)
10.1109/TIP.2014.2328894
Learning Object-to-Class Kernels for Scene Classification
Lei Zhang (2014)
10.1023/A:1010933404324
Random Forests
Leo Breiman (2004)
10.1109/CVPR.2014.477
Orientational Pyramid Matching for Recognizing Indoor Scenes
Lingxi Xie (2014)
Object Bank: A High-Level Image Representation for Scene Classification & Semantic Feature Sparsification
Li-Jia Li (2010)
Deep Convolutional Features for Image Based Retrieval and Scene Categorization
Arsalan Mousavian (2015)
10.2307/2530946
Classification and Regression Trees
Leo Breiman (1983)
10.1109/CVPR.2014.186
Scalable Multitask Representation Learning for Scene Classification
Maksim Lapin (2014)
10.1109/CVPR.2014.476
Learning Important Spatial Pooling Regions for Scene Classification
Di Lin (2014)
10.1145/2647868.2654889
Caffe: Convolutional Architecture for Fast Feature Embedding
Yangqing Jia (2014)
10.1109/TPAMI.2007.1155
A Thousand Words in a Scene
Pedro Quelhas (2007)
10.1109/CVPR.2012.6248107
Locality-constrained and spatially regularized coding for scene categorization
Aymen Shabou (2012)
10.1007/978-3-319-10584-0_26
Multi-scale Orderless Pooling of Deep Convolutional Activation Features
Yunchao Gong (2014)



This paper is referenced by
10.1109/JSTARS.2018.2809781
Cascaded Random Forest for Hyperspectral Image Classification
Youqiang Zhang (2018)
10.13053/rcs-139-1-2
Generación de un vector característico para la detección de intrusos en redes computacionales
Ana Alcántara-Ramírez (2017)
10.1007/978-3-030-00764-5_10
Particle Swarm Programming-Based Interactive Content-Based Image Retrieval
Xiao-Hui Yang (2018)
10.1142/s0129065718500119
Neonatal Seizure Detection Using Deep Convolutional Neural Networks
Amir Hossein Ansari (2019)
10.1101/396663
Interpretable multimodal deep learning for real-time pan-tissue pan-disease pathology search on social media
Andrew J. Schaumberg (2020)
10.1007/978-3-319-70096-0_45
Regularized Deep Convolutional Neural Networks for Feature Extraction and Classification
Khaoula Jayech (2017)
10.1007/978-3-319-63312-1_54
Improved Convolutional Neural Networks for Identifying Subcellular Localization of Gram-Negative Bacterial Proteins
Lei Wang (2017)
10.1007/s11042-018-6151-x
A scene image classification technique for a ubiquitous visual surveillance system
Maryam Asadzadeh Kaljahi (2018)
10.1109/ACCESS.2019.2908448
Scene Categorization Model Using Deep Visually Sensitive Features
Jing Shi (2019)
10.1109/ACCESS.2020.2992231
A New Convolutional Neural Network With Random Forest Method for Hydrogen Sensor Fault Diagnosis
Yongyi Sun (2020)
10.32470/ccn.2019.1079-0
Gestalt-based Contour Weights Improve Scene Categorization by CNNs
Morteza Rezanejad (2019)
10.1016/j.eswa.2018.08.056
Coordinate CNNs and LSTMs to categorize scene images with multi-views and multi-levels of abstraction
Shuang Bai (2019)
10.1016/J.CONBUILDMAT.2017.09.110
Deep Convolutional Neural Networks with transfer learning for computer vision-based data-driven pavement distress detection
Kasthurirangan Gopalakrishnan (2017)
10.1109/ACCESS.2020.2984657
A Parametric Optimization Oriented, AFSA Based Random Forest Algorithm: Application to the Detection of Cervical Epithelial Cells
Dong-yao Jia (2020)
10.1016/j.asoc.2018.03.007
Softly combining an ensemble of classifiers learned from a single convolutional neural network for scene categorization
Shuang Bai (2018)
10.1016/J.ESWA.2019.03.018
Informative trees by visual pruning
Carmela Iorio (2019)
10.7708/ijtte.2018.8(1).01
CRACK DAMAGE DETECTION IN UNMANNED AERIAL VEHICLE IMAGES OF CIVIL INFRASTRUCTURE USING PRE-TRAINED DEEP LEARNING MODEL
K. Gopalakrishnan (2018)
Deep Learning for Deepfakes Creation and Detection
Thanh Thi Nguyen (2019)
10.1016/j.neucom.2018.05.080
A survey on automatic image caption generation
Shuang Bai (2018)
10.1109/ICSAI.2017.8248532
An improved XGBoost based on weighted column subsampling for object classification
Xin Gao (2017)
10.1007/s00521-019-04515-z
Integration of textual cues for fine-grained image captioning using deep CNN and LSTM
Neeraj Gupta (2019)
10.1101/396663
Large-Scale Annotation of Histopathology Images from Social Media
Andrew J. Schaumberg (2018)
10.1109/CVPR.2019.00424
Scene Categorization From Contours: Medial Axis Based Salience Measures
Morteza Rezanejad (2019)
10.1007/978-3-319-68935-7_39
Object Recognition Based on Dynamic Random Forests and SURF Descriptor
Khaoula Jayech (2017)
10.2478/acss-2018-0018
An Efficient Technique for Size Reduction of Convolutional Neural Networks after Transfer Learning for Scene Recognition Tasks
Vadim V. Romanuke (2018)
10.1109/icccnt45670.2019.8944564
Tracking Eye Movements To Predict The Valence of A Scene
Sudarshana Tamuly (2019)
10.1007/978-3-030-33607-3_51
Deep Convolutional Neural Networks Based on Image Data Augmentation for Visual Object Recognition
Khaoula Jayech (2019)
10.1007/s12613-019-1724-x
A novel approach to predict green density by high-velocity compaction based on the materials informatics method
Kai-qi Zhang (2019)
10.1016/j.eswa.2017.12.029
Increasing diversity in random forest learning algorithm via imprecise probabilities
Joaquín Abellán (2018)
10.1016/j.eswa.2019.112912
A hybrid regularization approach for random vector functional-link networks
Hailiang Ye (2020)
10.1016/j.comcom.2020.04.033
Detection of algorithmically-generated domains: An adversarial machine learning approach
Mohammadhadi Alaeiyan (2020)
Semantic Scholar Logo Some data provided by SemanticScholar