Unrolling loopy top-down semantic feedback in convolutional deep networks

IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

Volumn , Issue , 2014, Pages 504-511

  Gatta, Carlo ^a   Romero, Adriana ^b   Van De Veijer, Joost ^a  

^a Barcelona Perception Computing Lab   (Spain)

^b UNIVERSITY OF BARCELONA   (Spain)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTER VISION; IMAGE ENHANCEMENT; SEMANTIC WEB; SEMANTICS;

GLOBAL APPEARANCES; IMAGE PARSING; STATE OF THE ART; STATE-OF-THE-ART METHODS; TOPDOWN;

CONVOLUTION;

EID: 84908530334     PISSN: 21607508     EISSN: 21607516     Source Type: Conference Proceeding    
DOI: 10.1109/CVPRW.2014.80     Document Type: Conference Paper

References (31)

1. Y. Bengio, P. Lamblin, D. Popovici, and H. Larochelle. Greedy layer-wise training of deep networks. In NIPS, pages 153-160, 2006. 1, 2, 3
2. X. Boix, J. M. Gonfaus, J. van de Weijer, A. D. Bagdanov, J. S. Gual, and J. Gonzàlez. Harmony potentials-fusing global and local scale for semantic image segmentation. IJCV, 96(1):83-102, 2012. 2
3. F. Ciompi, O. Pujol, and P. Radeva. Ecoc-drf: Discriminative random fields based on error-correcting output codes. Pattern Recognition, 47:2193-2204, 2014. 2
4. A. Coates, H. Lee, and A. Y. Ng. An analysis of singlelayer networks in unsupervised feature learning. In AISTATS, pages 214-223, 2011. 2
5. A. Coates and A. Ng. The importance of encoding versus training with sparse coding and vector quantization. In ICML, pages 921-928, 2011. 2
6. D. Eigen and R. Fergus. In CVPR, pages 2799-2806. 2
7. D. Erhan, Y. Bengio, A. Courville, P.-A. Manzagol, P. Vincent, and S. Bengio. Why does unsupervised pre-training help deep learning? JMLR, 11:625-660, Mar. 2010. 1
8. C. Farabet, C. Couprie, L. Najman, and Y. LeCun. Learning hierarchical features for scene labeling. IEEE TPAMI, 35(8):1915-1929, 2013. 1, 2, 3, 5, 6, 7
9. C. Gatta and F. Ciompi. Stacked sequential scale-space taylor context. IEEE TPAMI, 2014. 2
10. D. Grangier, L. Bottou, and R. Collobert. Deep convolutional networks for scene parsing. ICML 2009 Workshop on Learning Feature Hierarchies, June 2009. 1, 2
11. Q.-X. Huang, M. Han, B. Wu, and S. Ioffe. A hierarchical conditional random field model for labeling and segmenting images of street scenes. In CVPR, pages 1953-1960. IEEE, 2011. 2
12. J. Jiang and Z. Tu. Efficient scale space auto-context for image segmentation and labeling. In CVPR, pages 1810-1817. IEEE, 2009. 2
13. K. Kavukcuoglu, P. Sermanet, Y. Boureau, K. Gregor, M. Mathieu, and Y. LeCun. Learning convolutional feature hierachies for visual recognition. In NIPS, 2010. 2
14. P. Kohli, L. Ladicky, and P. H. S. Torr. Robust higher order potentials for enforcing label consistency. IJCV, 82(3):302-324, 2009. 2
15. L. Ladicky, C. Russell, P. Kohli, and P. H. S. Torr. Associative hierarchical crfs for object class image segmentation. In ICCV, pages 739-746. IEEE, 2009. 2
16. L. Ladicky, C. Russell, P. Kohli, and P. H. S. Torr. Graph cut based inference with co-occurrence statistics. In ECCV (5), volume 6315 of LNCS, pages 239-253. Springer, 2010. 2
17. H. Lee, C. Ekanadham, and A. Y. Ng. Sparse deep belief net model for visual area v2. In NIPS, pages 873-880, 2008. 2
18. C. Liu, J. Yuen, and A. Torralba. Nonparametric scene parsing via label transfer. IEEE TPAMI, 33(12):2368-2382, 2011. 2, 5
19. D. Munoz, J. A. D. Bagnell, and M. Hebert. Stacked hierarchical labeling. In ECCV, pages 57-70, 2010. 2
20. J. Ngiam, P. W. Koh, Z. Chen, S. Bhaskar, and A. Y. Ng. Sparse filtering. In NIPS, pages 1125-1133, 2011. 2
21. S. Nowozin, C. Rother, S. Bagon, T. Sharp, B. Yao, and P. Kholi. Decision tree fields. In ICCV, pages 1668-1675, 2011. 2
22. B. Olshausen and D. J. Field. Sparse coding with an overcomplete basis set: a strategy employed by v1? Vision Research, 37(23):3311-3325, 1997. 2
23. P. Pinheiro and R. Collobert. Recurrent convolutional neural networks for scene labeling. JMLR, 1(32):82-90, 2014. 1, 2, 3, 4, 5, 6
24. M. A. Ranzato, C. Poultney, S. Chopra, and Y. Lecun. Efficient learning of sparse representations with an energy-based model. In NIPS, pages 1137-1144, 2006. 2
25. A. Romero, P. Radeva, and C. Gatta. No more metaparameter tuning in unsupervised sparse feature learning. arXiv:1402. 5766, 2014. 2, 5
26. S. Rota Bulò, P. Kontschieder, M. Pelillo, and H. Bischof. Structured local predictors for image labelling. In CVPR, pages 3530-3537. IEEE, 2012. 2
27. P. Sermanet, K. Kavukcuoglu, S. Chintala, and Y. LeCun. Pedestrian detection with unsupervised multi-stage feature learning. In CVPR. 3
28. G. Singh and J. Kosecka. Nonparametric scene parsing with adaptive feature relevance and semantic context. In CVPR, pages 3151-3157. IEEE, 2013. 1, 2, 3, 5, 6
29. J. Tighe and S. Lazebnik. Superparsing-scalable nonparametric image parsing with superpixels. IJCV, 101(2):329-349, 2013. 2
30. Z. Tu and X. Bai. Auto-context and its application to highlevel vision tasks and 3d brain image segmentation. IEEE TPAMI, 32(10):1744-1757, 2010. 2
31. M. Ying Yang and W. Forstner. A hierarchical conditional random field model for labeling and classifying images of man-made scenes. In IEEE/ISPRS workshop on Computer Vision for Remote Sensing of the Environment, pages 196-203, 2011. 2