Gaussian Process Density Counting from Weak Supervision

As a novel learning setup, we introduce learning to count objects within an image from only region-level count information. This level of supervision is weaker than earlier approaches that require segmenting, drawing bounding boxes, or putting dots on centroids of all objects within training images. We devise a weakly supervised kernel learner that achieves higher count accuracies than previous counting models. We achieve this by placing a Gaussian process prior on a latent function the square of which is the count density. We impose non-negativeness and smooth the GP response as an intermediary step in model inference. We illustrate the effectiveness of our model on two benchmark applications: (i) synthetic cell and (ii) pedestrian counting, and one novel application: (iii) erythrocyte counting on blood samples of malaria patients.

[1]  Vincent Lepetit,et al.  You Should Use Regression to Detect Cells , 2015, MICCAI.

[2]  Andrew Zisserman,et al.  Microscopy cell counting with fully convolutional regression networks , 2015 .

[3]  Neil D. Lawrence,et al.  Gaussian Processes for Big Data , 2013, UAI.

[4]  Slobodan Vucetic,et al.  Mixture Model for Multiple Instance Regression and Applications in Remote Sensing , 2012, IEEE Transactions on Geoscience and Remote Sensing.

[5]  Fernando De la Torre,et al.  Gaussian Processes Multiple Instance Learning , 2010, ICML.

[6]  Anonymous Authors Empowering Multiple Instance Histopathology Cancer Diagnosis by Cell Graphs , 2014 .

[7]  Kiri Wagstaff,et al.  Multiple-Instance Regression with Structured Data , 2008, 2008 IEEE International Conference on Data Mining Workshops.

[8]  Andreas K. Maier,et al.  Unsupervised Unstained Cell Detection by SIFT Keypoint Clustering and Self-labeling Algorithm , 2014, MICCAI.

[9]  David Page,et al.  Multiple Instance Regression , 2001, ICML.

[10]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[11]  Neil D. Lawrence,et al.  Bayesian Gaussian Process Latent Variable Model , 2010, AISTATS.

[12]  Kiri L. Wagstaff,et al.  Salience Assignment for Multiple-Instance Regression , 2007 .

[13]  Andrew Zisserman,et al.  Learning to Detect Cells Using Non-overlapping Extremal Regions , 2012, MICCAI.

[14]  Nuno Vasconcelos,et al.  Privacy preserving crowd monitoring: Counting people without people models or tracking , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

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

[16]  Neil D. Lawrence,et al.  Gaussian Process Latent Variable Models for Visualisation of High Dimensional Data , 2003, NIPS.

[17]  Andrew Zisserman,et al.  Learning To Count Objects in Images , 2010, NIPS.

[18]  Tommy W. S. Chow,et al.  A neural-based crowd estimation by hybrid global learning algorithm , 1999, IEEE Trans. Syst. Man Cybern. Part B.

[19]  Stella X. Yu,et al.  Pop out many small structures from a very large microscopic image , 2011, Medical Image Anal..

[20]  Zoubin Ghahramani,et al.  Local and global sparse Gaussian process approximations , 2007, AISTATS.

[21]  Neil D. Lawrence,et al.  Deep Gaussian Processes , 2012, AISTATS.

[22]  David B. Dunson,et al.  Bayesian Data Analysis , 2010 .

[23]  Nuno Vasconcelos,et al.  Counting People With Low-Level Features and Bayesian Regression , 2012, IEEE Transactions on Image Processing.

[24]  Sridha Sridharan,et al.  Crowd Counting Using Multiple Local Features , 2009, 2009 Digital Image Computing: Techniques and Applications.

[25]  Ullrich Köthe,et al.  Learning to count with regression forest and structured labels , 2012, Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012).

[26]  Zoubin Ghahramani,et al.  Collaborative Gaussian Processes for Preference Learning , 2012, NIPS.

[27]  Chong Wang,et al.  Stochastic variational inference , 2012, J. Mach. Learn. Res..

[28]  Andrei Popescu-Belis,et al.  Explaining the Stars: Weighted Multiple-Instance Learning for Aspect-Based Sentiment Analysis , 2014, EMNLP.

[29]  Matthias W. Seeger,et al.  Using the Nyström Method to Speed Up Kernel Machines , 2000, NIPS.

[30]  Neil D. Lawrence,et al.  Fast Variational Inference in the Conjugate Exponential Family , 2012, NIPS.

[31]  Hai Tao,et al.  A Viewpoint Invariant Approach for Crowd Counting , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[32]  Sridha Sridharan,et al.  Crowd Counting Using Group Tracking and Local Features , 2010, 2010 7th IEEE International Conference on Advanced Video and Signal Based Surveillance.

[33]  Andrew Zisserman,et al.  Interactive Object Counting , 2014, ECCV.