Learning Covariant Feature Detectors

Local covariant feature detection, namely the problem of extracting viewpoint invariant features from images, has so far largely resisted the application of machine learning techniques. In this paper, we propose the first fully general formulation for learning local covariant feature detectors. We propose to cast detection as a regression problem, enabling the use of powerful regressors such as deep neural networks. We then derive a covariance constraint that can be used to automatically learn which visual structures provide stable anchors for local feature detection. We support these ideas theoretically, proposing a novel analysis of local features in term of geometric transformations, and we show that all common and many uncommon detectors can be derived in this framework. Finally, we present empirical results on translation and rotation covariant detectors on standard feature benchmarks, showing the power and flexibility of the framework.

[1]  Azriel Rosenfeld,et al.  Angle Detection on Digital Curves , 1973, IEEE Transactions on Computers.

[2]  Larry S. Davis,et al.  A Corner-Finding Algorithm for Chain-Coded Curves , 1977, IEEE Transactions on Computers.

[3]  P. Sankar,et al.  A parallel procedure for the detection of dominant points on a digital curve , 1978 .

[4]  Paul Beaudet,et al.  Rotationally invariant image operators , 1978 .

[5]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[6]  Antonio Guiducci,et al.  Corner characterization by differential geometry techniques , 1988, Pattern Recognit. Lett..

[7]  Tony Lindeberg,et al.  Shape-Adapted Smoothing in Estimation of 3-D Depth Cues from Affine Distortions of Local 2-D Brightness Structure , 1994, ECCV.

[8]  Vikram Srinivasan,et al.  A neural network based corner detection method , 1995, Proceedings of ICNN'95 - International Conference on Neural Networks.

[9]  Cordelia Schmid,et al.  Local Grayvalue Invariants for Image Retrieval , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Tony Lindeberg,et al.  Scale-Space Theory in Computer Vision , 1993, Lecture Notes in Computer Science.

[11]  Tony Lindeberg,et al.  Shape-adapted smoothing in estimation of 3-D shape cues from affine deformations of local 2-D brightness structure , 1997, Image Vis. Comput..

[12]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[13]  S. Mallat A wavelet tour of signal processing , 1998 .

[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]  Cordelia Schmid,et al.  Matching images with different resolutions , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[16]  Adam Baumberg,et al.  Reliable feature matching across widely separated views , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[17]  Luc Van Gool,et al.  Wide Baseline Stereo Matching based on Local, Affinely Invariant Regions , 2000, BMVC.

[18]  Cordelia Schmid,et al.  Indexing Based on Scale Invariant Interest Points , 2001, ICCV.

[19]  Andrew Zisserman,et al.  Viewpoint invariant texture matching and wide baseline stereo , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[20]  Stepán Obdrzálek,et al.  Local affine frames for wide-baseline stereo , 2002, Object recognition supported by user interaction for service robots.

[21]  Cordelia Schmid,et al.  An Affine Invariant Interest Point Detector , 2002, ECCV.

[22]  Michael Brady,et al.  Saliency, Scale and Image Description , 2001, International Journal of Computer Vision.

[23]  Bill Triggs,et al.  Detecting Keypoints with Stable Position, Orientation, and Scale under Illumination Changes , 2004, ECCV.

[24]  Stephen M. Smith,et al.  SUSAN—A New Approach to Low Level Image Processing , 1997, International Journal of Computer Vision.

[25]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[26]  Tony Lindeberg,et al.  Feature Detection with Automatic Scale Selection , 1998, International Journal of Computer Vision.

[27]  Karl Rohr,et al.  Recognizing corners by fitting parametric models , 1992, International Journal of Computer Vision.

[28]  B. S. Manjunath,et al.  A Mathematical Comparison of Point Detectors , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[29]  Tom Drummond,et al.  Fusing points and lines for high performance tracking , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[30]  Bernhard Schölkopf,et al.  Learning an Interest Operator from Human Eye Movements , 2006, 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06).

[31]  Tom Drummond,et al.  Machine Learning for High-Speed Corner Detection , 2006, ECCV.

[32]  Leonardo Trujillo,et al.  Synthesis of interest point detectors through genetic programming , 2006, GECCO.

[33]  Jiri Matas,et al.  Learning Fast Emulators of Binary Decision Processes , 2009, International Journal of Computer Vision.

[34]  Tom Drummond,et al.  Faster and Better: A Machine Learning Approach to Corner Detection , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[35]  Bodo Rosenhahn,et al.  Increasing the accuracy of feature evaluation benchmarks using differential evolution , 2011, 2011 IEEE Symposium on Differential Evolution (SDE).

[36]  Leonardo Trujillo,et al.  Evolutionary-computer-assisted design of image operators that detect interest points using genetic programming , 2011, Image Vis. Comput..

[37]  Henrik Aanæs,et al.  Interesting Interest Points , 2011, International Journal of Computer Vision.

[38]  Stefan Holzer,et al.  Learning to Efficiently Detect Repeatable Interest Points in Depth Data , 2012, ECCV.

[39]  Andrew Zisserman,et al.  Descriptor Learning Using Convex Optimisation , 2012, ECCV.

[40]  Andrea Vedaldi,et al.  MatConvNet: Convolutional Neural Networks for MATLAB , 2014, ACM Multimedia.

[41]  Cordelia Schmid,et al.  Local Convolutional Features with Unsupervised Training for Image Retrieval , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[42]  Yann LeCun,et al.  Computing the stereo matching cost with a convolutional neural network , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[43]  Iasonas Kokkinos,et al.  Discriminative Learning of Deep Convolutional Feature Point Descriptors , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[44]  Iasonas Kokkinos,et al.  Modeling local and global deformations in Deep Learning: Epitomic convolution, Multiple Instance Learning, and sliding window detection , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[45]  Rahul Sukthankar,et al.  MatchNet: Unifying feature and metric learning for patch-based matching , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[46]  Nikos Komodakis,et al.  Learning to compare image patches via convolutional neural networks , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[47]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[48]  Vincent Lepetit,et al.  Learning to Assign Orientations to Feature Points , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).