Abstract
The problem of holistic scene understanding involves many vision tasks such as depth estimation, scene categorization, event categorization, etc. Each of these tasks explores some aspects of the scene but, these tasks are related in that, they represent attributes of the same scene. An intuition is that one task can provide meaningful attributes to aid the learning process of another task. In this work, we propose a generic model (together with learning and inference techniques) for connecting different vision tasks in the form of a 2-layer cascade. Our model considers the first layer as a hidden layer, where the latent variables are inferred by feedback from the second layer. The feedback mechanism allows the first layer classifiers to focus on more important image modes, and draws their output towards “attributes” rather than the original “labels”. Our model also automatically discovers sparse connections between the learned attributes on the first layer and the target task on the second layer. Note that in our model, the same vision tasks can act as attribute learners as well as target tasks, while being set up on different layers. In extensive experiments, we show that the same proposed model improves the performance in all the tasks we consider: single image depth estimation, scene categorization, saliency detection and event categorization.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Saxena, A., Chung, S.H., Ng, A.Y.: 3-D depth reconstruction from a single still image. IJCV 76, 53–69 (2007)
Li, L.J., Socher, R., Fei-Fei, L.: Towards total scene understanding: Classification, annotation and segmentation in an automatic framework. In: CVPR (2009)
Hoiem, D., Efros, A.A., Hebert, M.: Closing the loop on scene interpretation. In: CVPR (2008)
Sudderth, E.B., Torralba, A., Freeman, W.T., Willsky, A.S.: Depth from familiar objects: A hierarchical model for 3D scenes. In: CVPR (2006)
Heitz, G., Gould, S., Saxena, A., Koller, D.: Cascaded classification models: Combining models for holistic scene understanding. In: NIPS (2008)
Ferrari, V., Zisserman, A.: Learning visual attributes. In: NIPS (2007)
Farhadi, A., Endres, I., Hoiem, D., Forsyth, D.: Describing objects by their attributes. In: CVPR (2009)
Lampert, C., Nickisch, H., Harmeling, S.: Learning to detect unseen object classes by between-class attribute transfer. In: CVPR (2009)
Wang, G., Forsyth, D.: Joint learning of visual attributes, object classes and visual saliency. In: ICCV (2009)
Sudderth, E.B., Torralba, A., Freeman, W.T., Willsky, A.S.: Learning hierarchical models of scenes, objects, and parts. In: ICCV (2005)
Hoiem, D., Efros, A.A., Hebert, M.: Putting objects in perspective. In: CVPR (2006)
Tu, Z., Chen, X., Yuille, A.L., Zhu, S.: Image parsing: Unifying segmentation, detection, and recognition. In: ICCV (2003)
Kumar, S., Hebert, M.: A hierarchical field framework for unified context-based classification. In: ICCV (2005)
Li, L.J., Fei-Fei, L.: What, where and who? classifying event by scene and object recognition. In: ICCV (2007)
Freund, Y., Schapire, R.E.: A decision-theoretic generalization of on-line learning and an application to boosting. In: EuroCOLT (1995)
Lee, H., Battle, A., Raina, R., Ng, A.Y.: Efficient sparse coding algorithms. In: NIPS (2007)
Mairal, J., Leordeanu, M., Bach, F., Hebert, M., Ponce, J.: Discriminative Sparse Image Models for Class-Specific Edge Detection and Image Interpretation. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part III. LNCS, vol. 5304, pp. 43–56. Springer, Heidelberg (2008)
Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the em algorithm. J. of Royal Stat. Soc., Series B 39, 1–38 (1977)
Gibbs, M., Mackay, D.: Variational gaussian process classifiers. IEEE Transactions on Neural Networks 11, 1458–1464 (1997)
Torralba, A., Oliva, A., Castelhano, M.S., Henderson, J.M.: Contextual guidance of eye movements and attention in real-world scenes: the role of global features in object search. Psychol. Rev. 113, 766–786 (2006)
Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part based models. PAMI 99 (2009)
Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: Pascal, voc2008 (2008), http://www.pascal-network.org/challenges/VOC/voc2008/workshop/index.html
Oliva, A., Torralba, A.: Modeling the shape of the scene: A holistic representation of the spatial envelope. IJCV 42, 145–175 (2001)
Oliva, A., Torralba, A.: Mit outdoor scene dataset (2009), http://people.csail.mit.edu/torralba/code/spatialenvelope/
Achanta, R., Hemami, S., Estrada, F., Susstrunk, S.: Frequency-tuned Salient Region Detection. In: CVPR (2009)
Saxena, A., Sun, M., Ng, A.: Make3D: Learning 3D scene structure from a single still image. PAMI 31, 824–840 (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Li, C., Kowdle, A., Saxena, A., Chen, T. (2012). A Generic Model to Compose Vision Modules for Holistic Scene Understanding. In: Kutulakos, K.N. (eds) Trends and Topics in Computer Vision. ECCV 2010. Lecture Notes in Computer Science, vol 6553. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-35749-7_6
Download citation
DOI: https://doi.org/10.1007/978-3-642-35749-7_6
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-35748-0
Online ISBN: 978-3-642-35749-7
eBook Packages: Computer ScienceComputer Science (R0)