Learning in Computer Vision: Some Thoughts

It is argued that the ability to generalise is the most important characteristic of learning and that generalisation may be achieved only if pattern recognition systems learn the rules of meta-knowledge rather than the labels of objects. A structure, called "tower of knowledge", according to which knowledge may be organised, is proposed. A scheme of interpreting scenes using the tower of knowledge and aspects of utility theory is also proposed. Finally, it is argued that globally consistent solutions of labellings are neither possible, nor desirable for an artificial cognitive system.

[1]  William J. Christmas,et al.  Structural Matching in Computer Vision Using Probabilistic Relaxation , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[3]  Václav Hlavác,et al.  Ten Lectures on Statistical and Structural Pattern Recognition , 2002, Computational Imaging and Vision.

[4]  Maria Petrou,et al.  Image processing - dealing with texture , 2020 .

[5]  Steven W. Zucker,et al.  On the Foundations of Relaxation Labeling Processes , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Paul A. Viola,et al.  Learning from one example through shared densities on transforms , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[7]  Patrick Henry Winston,et al.  Learning structural descriptions from examples , 1970 .

[8]  David L. Waltz,et al.  Understanding Line drawings of Scenes with Shadows , 1975 .

[9]  Ernest Nagel,et al.  Gödel's Proof , 1958 .

[10]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[11]  J. Tenenbaum,et al.  Theory-based Bayesian models of inductive learning and reasoning , 2006, Trends in Cognitive Sciences.

[12]  Maria Petrou,et al.  Obtaining The Correspondence between Bayesian and Neural Networks , 1998, Int. J. Pattern Recognit. Artif. Intell..

[13]  Z Li,et al.  Visual segmentation by contextual influences via intra-cortical interactions in the primary visual cortex. , 1999, Network.

[14]  Patrick Henry Winston,et al.  The psychology of computer vision , 1976, Pattern Recognit..

[15]  Allen R. Hanson,et al.  Bayesian networks and utility theory for the management of uncertainty and control of algorithms in vision systems , 2002 .

[16]  Lotfi A. Zadeh,et al.  A fuzzy-algorithmic approach to the definition of complex or imprecise concepts , 1976 .

[17]  Zhaoping Li,et al.  A Neural Model of Contour Integration in the Primary Visual Cortex , 1998, Neural Computation.

[18]  Josef Kittler,et al.  On the Foundations of Probabilistic Relaxation with Product Support , 1998, Journal of Mathematical Imaging and Vision.

[19]  J. Laurie Snell,et al.  Markov Random Fields and Their Applications , 1980 .

[20]  Zhaoping Li,et al.  Computational Design and Nonlinear Dynamics of a Recurrent Network Model of the Primary Visual Cortex , 2001, Neural Computation.

[21]  Maria Petrou,et al.  Non-Gibbsian Markov Random Field Models for Contextual Labelling of Structured Scenes , 2007, BMVC.

[22]  Adolfo Guzmán-Arenas,et al.  COMPUTER RECOGNITION OF THREE-DIMENSIONAL OBJECTS IN A VISUAL SCENE , 1968 .

[23]  Daphne Koller,et al.  Support Vector Machine Active Learning with Applications to Text Classification , 2000, J. Mach. Learn. Res..

[24]  Richard Kendall Miller,et al.  Expert Systems Handbook: An Assessment of Technology and Applications , 1990 .