In many recent object recognition systems, feature extraction
stages are generally composed of a filter bank, a
non-linear transformation, and some sort of feature pooling
layer...
Kevin Jarrett, Koray Kavukcuoglu, Marc’Aurelio R...
This paper deals with the performance evaluation of three object invariant descriptors : Hu moments, Zernike moments and Fourier-Mellin descriptors. Experiments are conducted on a...
Recent work on unsupervised feature learning has shown that learning on polynomial expansions of input patches, such as on pair-wise products of pixel intensities, can improve the...
A key challenge in applying kernel-based methods for discriminative learning is to identify a suitable kernel given a problem domain. Many methods instead transform the input data...
Many modern visual recognition algorithms incorporate a step of spatial `pooling', where the outputs of several nearby feature detectors are combined into a local or global `...