2016

Knowledge Guided Disambiguation for Large-Scale Scene Classification with Multi-Resolution CNNs

Wang, Limin, Guo, Sheng, Huang, Weilin et al.

Understand

Convolutional Neural Networks (CNNs) have made remarkable progress on scene recognition, partially due to these recent large-scale scene datasets, such as the Places and Places2.

Scene categories are often defined by multi-level information, including local objects, global layout, and background environment, thus leading to large intra-class variations.
In addition, with the increasing number of scene categories, label ambiguity has become another crucial issue in large-scale classification.
This paper focuses on large-scale scene recognition and makes two major contributions to tackle these issues.

Built on

Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-based learning applied to document recognition,” Proceedings of the IEEE , vol. 86, no. 11, pp. 2278–2324, 1998
1998
Earlier work this paper cites.
A. Oliva and A. Torralba, “Modeling the shape of the scene: A holistic representation of the spatial envelope,” International Journal of Computer Vision , vol. 42, no. 3, pp. 145–175, 2001
2001
Earlier work this paper cites.
A. Torralba, “Contextual priming for object detection,” International Journal of Computer Vision , vol. 53, no. 2, pp. 169–191, 2003
2003
Earlier work this paper cites.
F. Li and P. Perona, “A bayesian hierarchical model for learning natural scene categories,” in CVPR , 2005, pp. 524–531
2005
Earlier work this paper cites.
S. Lazebnik, C. Schmid, and J. Ponce, “Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories,” in CVPR , 2006, pp. 2169–2178
2006
Earlier work this paper cites.
C. Bucila, R. Caruana, and A. Niculescu-Mizil, “Model compression,” in SIGKDD , 2006, pp. 535–541
2006
Earlier work this paper cites.
J. Deng, W. Dong, R. Socher, L. Li, K. Li, and F. Li, “ImageNet: A large-scale hierarchical image database,” in CVPR , 2009, pp. 248–255
2009
Earlier work this paper cites.
A. Quattoni and A. Torralba, “Recognizing indoor scenes,” in CVPR , 2009, pp. 413–420
2009
Earlier work this paper cites.
A. Oliva, “Scene perception,” Encyclopaedia of Perception , 2009
2009
Earlier work this paper cites.
P. F. Felzenszwalb, R. B. Girshick, D. A. McAllester, and D. Ramanan, “Object detection with discriminatively trained part-based models,” IEEE Trans. Pattern Anal. Mach. Intell. , vol. 32, no. 9, pp. 1627–1645, 2010
2010
Earlier work this paper cites.
J. Xiao, J. Hays, K. A. Ehinger, A. Oliva, and A. Torralba, “SUN database: Large-scale scene recognition from abbey to zoo,” in CVPR , 2010, pp. 3485–3492
2010
Earlier work this paper cites.
J. Wu and J. M. Rehg, “CENTRIST: A visual descriptor for scene categorization,” IEEE Trans. Pattern Anal. Mach. Intell. , vol. 33, no. 8, pp. 1489–1501, 2011
2011
Earlier work this paper cites.
L. Wang, Y. Wu, T. Lu, and K. Chen, “Multiclass object detection by combining local appearances and context,” in ACM Multimedia , 2011, pp. 1161–1164
2011
Earlier work this paper cites.
M. Pandey and S. Lazebnik, “Scene recognition and weakly supervised object localization with deformable part-based models,” in ICCV , 2011, pp. 1307–1314
2011
Earlier work this paper cites.
C. Chang and C. Lin, “LIBSVM: A library for support vector machines,” ACM TIST , vol. 2, no. 3, p. 27, 2011
2011
Earlier work this paper cites.
S. N. Parizi, J. G. Oberlin, and P. F. Felzenszwalb, “Reconfigurable models for scene recognition,” in CVPR , 2012, pp. 2775–2782
2012
Earlier work this paper cites.
S. Singh, A. Gupta, and A. A. Efros, “Unsupervised discovery of mid-level discriminative patches,” in ECCV , 2012, pp. 73–86
2012
Earlier work this paper cites.
A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” in NIPS , 2012, pp. 1106–1114
2012
Earlier work this paper cites.
M. Juneja, A. Vedaldi, C. V. Jawahar, and A. Zisserman, “Blocks that shout: Distinctive parts for scene classification,” in CVPR , 2013, pp. 923–930
2013
Earlier work this paper cites.
L. Zhang, X. Zhen, and L. Shao, “Learning object-to-class kernels for scene classification,” IEEE Trans. Image Processing , vol. 23, no. 8, pp. 3241–3253, 2014
2014
Earlier work this paper cites.

Similar

Z. Zuo, G. Wang, B. Shuai, L. Zhao, Q. Yang, and X. Jiang, “Learning discriminative and shareable features for scene classification,” in ECCV , 2014, pp. 552–568
2014
Cited alongside, same era.
Y. Gong, L. Wang, R. Guo, and S. Lazebnik, “Multi-scale orderless pooling of deep convolutional activation features,” in ECCV , 2014, pp. 392–407
2014
Cited alongside, same era.
L. Xie, J. Wang, B. Guo, B. Zhang, and Q. Tian, “Orientational pyramid matching for recognizing indoor scenes,” in CVPR , 2014, pp. 3734–3741
2014
Cited alongside, same era.
L. Wang, Y. Qiao, and X. Tang, “Latent hierarchical model of temporal structure for complex activity classification,” IEEE Trans. Image Processing , vol. 23, no. 2, pp. 810–822, 2014
2014
Cited alongside, same era.
B. Zhou, À. Lapedriza, J. Xiao, A. Torralba, and A. Oliva, “Learning deep features for scene recognition using places database,” in NIPS , 2014, pp. 487–495
2014
Cited alongside, same era.
M. D. Zeiler and R. Fergus, “Visualizing and understanding convolutional networks,” in ECCV , 2014, pp. 818–833
2014
Cited alongside, same era.
K. He, X. Zhang, S. Ren, and J. Sun, “Spatial pyramid pooling in deep convolutional networks for visual recognition,” in ECCV , 2014, pp. 346–361
2014
Cited alongside, same era.
K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” CoRR , vol. abs/1409.1556, 2014
Original
2014
Cited alongside, same era.
A. Romero, N. Ballas, S. E. Kahou, A. Chassang, C. Gatta, and Y. Bengio, “Fitnets: Hints for thin deep nets,” CoRR , vol. abs/1412.6550, 2014
Original
2014
Cited alongside, same era.
S. Yang and D. Ramanan, “Multi-scale recognition with DAG-CNNs,” in ICCV , 2015, pp. 1215–1223
2015
Cited alongside, same era.
L. Wang, Z. Wang, W. Du, and Y. Qiao, “Object-scene convolutional neural networks for event recognition in images,” in CVPR Workshops , 2015, pp. 30–35
2015
Cited alongside, same era.
Y. Xiong, K. Zhu, D. Lin, and X. Tang, “Recognize complex events from static images by fusing deep channels,” in CVPR , 2015, pp. 1600–1609
2015
Cited alongside, same era.

Then

L. Wang, S. Guo, W. Huang, and Y. Qiao, “Places205-vggnet models for scene recognition,” CoRR , vol. abs/1508.01667, 2015
Original
2015
Later among the works it cites.
B. Gao, X. Wei, J. Wu, and W. Lin, “Deep spatial pyramid: The devil is once again in the details,” CoRR , vol. abs/1504.05277, 2015
Original
2015
Later among the works it cites.
H. Yang, J. T. Zhou, Y. Zhang, B. Gao, J. Wu, and J. Cai, “Can partial strong labels boost multi-label object recognition?” CoRR , vol. abs/1504.05843, 2015
Original
2015
Later among the works it cites.
L. Shen, Z. Lin, and Q. Huang, “Relay backpropagation for effective learning of deep convolutional neural networks,” in ECCV , 2016, pp. 467–482
2016
Closest in time.
Z. Zuo, B. Shuai, G. Wang, X. Liu, X. Wang, B. Wang, and Y. Chen, “Learning contextual dependence with convolutional hierarchical recurrent neural networks,” IEEE Trans. Image Processing , vol. 25, no. 7, pp. 2983–2996, 2016
2016
Closest in time.
Z. Wang, L. Wang, Y. Wang, B. Zhang, and Y. Qiao, “Weakly supervised patchnets: Describing and aggregating local patches for scene recognition,” CoRR , vol. abs/1609.00153, 2016
Original
2016
Closest in time.
L. Wang, Z. Wang, Y. Qiao, and L. V. Gool, “Transferring object-scene convolutional neural networks for event recognition in still images,” CoRR , vol. abs/1609.00162, 2016
Original
2016
Closest in time.
L. Wang, Y. Qiao, and X. Tang, “MoFAP: A multi-level representation for action recognition,” International Journal of Computer Vision , vol. 119, no. 3, pp. 254–271, 2016
2016
Closest in time.
Y. Zhang, L. Cheng, J. Wu, J. Cai, M. N. Do, and J. Lu, “Action recognition in still images with minimum annotation efforts,” IEEE Trans. Image Processing , vol. 25, no. 11, pp. 5479–5490, 2016
2016
Closest in time.
B. Zhou, A. Khosla, À. Lapedriza, A. Torralba, and A. Oliva, “Places: An image database for deep scene understanding,” CoRR , vol. abs/1610.02055, 2016
Original
2016
Closest in time.
C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, “Rethinking the inception architecture for computer vision,” in CVPR , 2016, pp. 2818–2826
2016
Closest in time.
K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in CVPR , 2016, pp. 770–778
2016
Closest in time.
Y. Zhang, X. Wei, J. Wu, J. Cai, J. Lu, V. A. Nguyen, and M. N. Do, “Weakly supervised fine-grained categorization with part-based image representation,” IEEE Trans. Image Processing , vol. 25, no. 4, pp. 1713–1725, 2016
2016
Closest in time.
S. Gupta, J. Hoffman, and J. Malik, “Cross modal distillation for supervision transfer,” in CVPR , 2016, pp. 2827–2836
2016
Closest in time.
B. Zhang, L. Wang, Z. Wang, Y. Qiao, and H. Wang, “Real-time action recognition with enhanced motion vector CNNs,” in CVPR , 2016, pp. 2718–2726
2016
Closest in time.
L. Wang, Y. Xiong, Z. Wang, Y. Qiao, D. Lin, X. Tang, and L. Van Gool, “Temporal segment networks: Towards good practices for deep action recognition,” in ECCV , 2016, pp. 20–36
2016
Closest in time.
G. Xie, X. Zhang, S. Yan, and C. Liu, “Hybrid CNN and dictionary-based models for scene recognition and domain adaptation,” CoRR , vol. abs/1601.07977, 2016
Original
2016
Closest in time.
L. Herranz, S. Jiang, and X. Li, “Scene recognition with cnns: Objects, scales and dataset bias,” in CVPR , 2016, pp. 571–579
2016
Closest in time.
H. Yang, J. T. Zhou, and J. Cai, “Improving multi-label learning with missing labels by structured semantic correlations,” in ECCV , 2016, pp. 835–851
2016
Closest in time.
S. Guo, W. Huang, L. Wang, and Y. Qiao, “Locally supervised deep hybrid model for scene recognition,” IEEE Trans. Image Processing , vol. 26, no. 2, pp. 808–820, 2017
2017
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…