FlowBoost — Appearance learning from sparsely annotated video

We propose a new learning method which exploits temporal consistency to successfully learn a complex appearance model from a sparsely labeled training video. Our approach consists in iteratively improving an appearance-based model built with a Boosting procedure, and the reconstruction of trajectories corresponding to the motion of multiple targets. We demonstrate the efficiency of our procedure on pedestrian detection in videos and cell detection in microscopy image sequences. In both cases, our method is demonstrated to reduce the labeling requirement by one to two orders of magnitude. We show that in some instances, our method trained with sparse labels on a video sequence is able to outperform a standard learning procedure trained with the fully labeled sequence.

[1]  H. J. Scudder,et al.  Probability of error of some adaptive pattern-recognition machines , 1965, IEEE Trans. Inf. Theory.

[2]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[3]  Thorsten Joachims,et al.  Transductive Inference for Text Classification using Support Vector Machines , 1999, ICML.

[4]  J. Friedman.  Special Invited Paper-Additive logistic regression: A statistical view of boosting , 2000 .

[5]  Avrim Blum,et al.  Learning from Labeled and Unlabeled Data using Graph Mincuts , 2001, ICML.

[6]  Tommi S. Jaakkola,et al.  Partially labeled classification with Markov random walks , 2001, NIPS.

[7]  Zoubin Ghahramani,et al.  Learning from labeled and unlabeled data with label propagation , 2002 .

[8]  Thorsten Joachims,et al.  Transductive Learning via Spectral Graph Partitioning , 2003, ICML.

[9]  Neil D. Lawrence,et al.  Semi-supervised Learning via Gaussian Processes , 2004, NIPS.

[10]  Sebastian Thrun,et al.  Text Classification from Labeled and Unlabeled Documents using EM , 2000, Machine Learning.

[11]  D. Geman,et al.  Stationary Features and Cat Detection , 2008 .

[12]  Jiri Matas,et al.  Online learning of robust object detectors during unstable tracking , 2009, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops.

[13]  Pascal Fua,et al.  Joint pose estimator and feature learning for object detection , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[14]  Jiri Matas,et al.  P-N learning: Bootstrapping binary classifiers by structural constraints , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[15]  Pascal Fua,et al.  Ieee Transactions on Pattern Analysis and Machine Intelligence 1 Multiple Object Tracking Using K-shortest Paths Optimization , 2022 .