Synapse maintenance in the Where-What Networks

General object recognition in complex backgrounds is still challenging. On one hand, the various backgrounds, where object may appear at different locations, make it difficult to find the object of interest. On the other hand, with the numbers of locations, types and variations in each type (e.g., rotation) increasing, conventional model-based approaches start to break down. The Where-What Networks (WWNs) were a biologically inspired framework for recognizing learned objects (appearances) from complex backgrounds. However, they do not have an adaptive receptive field for an object of a curved contour. Leaked-in background pixels will cause problems when different objects look similar. This work introduces a new biologically inspired mechanism - synapse maintenance and uses both supervised (motor-supervised for class response) and unsupervised learning (synapse maintenance) to realize objects recognition. Synapse maintenance is meant to automatically decide which synapse should be active firing of the post-synaptic neuron. With the synapse maintenance, the network has achieved a significant improvement in the network performance.

[1]  Juyang Weng,et al.  WWN-2: A biologically inspired neural network for concurrent visual attention and recognition , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

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

[3]  Thomas Serre,et al.  Robust Object Recognition with Cortex-Like Mechanisms , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Juyang Weng,et al.  Where-What Network 3: Developmental top-down attention for multiple foregrounds and complex backgrounds , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

[5]  Juyang Weng,et al.  Where-what network 1: “Where” and “what” assist each other through top-down connections , 2008, 2008 7th IEEE International Conference on Development and Learning.

[6]  T. Poggio,et al.  Hierarchical models of object recognition in cortex September 23 , 1999 , 1999 .

[7]  Juyang Weng,et al.  Where-what network-4: The effect of multiple internal areas , 2010, 2010 IEEE 9th International Conference on Development and Learning.

[8]  Juyang Weng,et al.  Topographic Class Grouping with applications to 3D object recognition , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).