Factorizing appearance using epitomic flobject analysis

Previously, `flobject analysis' was introduced as a method for using motion or stereo disparity information to train better models of static images. During training, but not during testing, optic flow is used as a cue for factorizing appearance-based image features into those belonging to different flow-defined objects, or flobjects. Here, we describe how the image epitome can be extended to model flobjects and introduce a suitable learning algorithm. Using the CityCars and City F'edestrians datasets, we study the tasks of object classification and localization. Our method performs significantly better than the original LDA-based flobject analysis technique, SIFT-based methods with and without spatial pyramid matching, and gist descriptors.

[1]  K. Lempert,et al.  CONDENSED 1,3,5-TRIAZEPINES - IV THE SYNTHESIS OF 2,3-DIHYDRO-1H-IMIDAZO-[1,2-a] [1,3,5] BENZOTRIAZEPINES , 1983 .

[2]  J. Weickert,et al.  Lucas/Kanade meets Horn/Schunck: combining local and global optic flow methods , 2005 .

[3]  Jitendra Malik,et al.  Normalized cuts and image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[4]  Cordelia Schmid,et al.  Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[5]  Yann LeCun,et al.  Convolutional Learning of Spatio-temporal Features , 2010, ECCV.

[6]  Brendan J. Frey,et al.  Epitomic analysis of appearance and shape , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[7]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[8]  Ethan M. Meyers,et al.  Visual Parsing After Recovery From Blindness , 2009, Psychological science.

[9]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[10]  Brendan J. Frey,et al.  Learning better image representations using ‘flobject analysis’ , 2011, CVPR 2011.

[11]  Leslie Pack Kaelbling,et al.  Segmentation According to Natural Examples: Learning Static Segmentation from Motion Segmentation , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Alexei A. Efros,et al.  Discovering objects and their location in images , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[13]  Antonio Torralba,et al.  Building the gist of a scene: the role of global image features in recognition. , 2006, Progress in brain research.

[14]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[15]  Alexei A. Efros,et al.  Using Multiple Segmentations to Discover Objects and their Extent in Image Collections , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[16]  Yong Jae Lee,et al.  Collect-cut: Segmentation with top-down cues discovered in multi-object images , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.