Multiclass Object Recognition with Sparse, Localized Features
Jim Mutch, David G. Lowe · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2006
We apply a biologically inspired model of visual object recognition to the multiclass object categorization problem. Our model modifies that of Serre, Wolf, and Poggio. As in that work, we first apply Gabor filters at all positions and scales; feature complexity and position/scale invariance are then built up by alternating template matching and max pooling operations. We refine the approach in several biologically plausible ways, using simple versions of sparsification and lateral inhibition. We demonstrate the value of retaining some position and scale information above the intermediate feature level. Using feature selection we arrive at a model that performs better with fewer features. Our final model is tested on the Caltech 101 object categories and the UIUC car localization task, in both cases achieving state-of-the-art performance. The results strengthen the case for using this class of model in computer vision.
Cited by 453 works. doi:10.1109/cvpr.2006.200
Authors
References
- Gradient-based learning applied to document recognition
- Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position
- Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
- Receptive fields of single neurones in the cat's striate cortex
- Object class recognition by unsupervised scale-invariant learning
- Learning generative visual models from few training examples: An incremental Bayesian approach tested on 101 object categories
- Emergence of simple-cell receptive field properties by learning a sparse code for natural images
- Visual categorization with bags of keypoints
- The pyramid match kernel: discriminative classification with sets of image features
- Robust Object Recognition with Cortex-Like Mechanisms