18 May 2024 in Neural Networks
1 January 2016 in Neurocomputing
1 January 2011 in Pattern Recognition
IDIsabelle Debled-Rennesson
Isabelle Debled-Rennesson
8 March 2024 in IEEE Transactions on Neural Networks and Learning Systems
Network compression techniques that combine tensor decompositions and pruning have shown promise in leveraging the advantages of both strategies. In this work, we propose enhanced Network cOmpRession through TensOr decompositions and pruNing (NORTON), a novel method for network compression. NORTON introduces the concept of filter decomposition, enabling a more detailed decomposition of the network while preserving the weight’s multidimensional properties. Our method incorporates a novel structured pruning approach, effectively integrating the decomposed model. Through extensive experiments on various architectures, benchmark datasets, and representative vision tasks, we demonstrate the usefulness of our method. NORTON achieves superior results compared to state-of-the-art (SOTA) techniques in terms of complexity and accuracy. Our code is also available for research purposes.
1 June 2014 in Image and Vision Computing
12 December 2016 in EURASIP Journal on Image and Video Processing
By estimating the first-order (direction) and second-order (curvature) derivatives in an image, the parameters of a line or circle passing through a point may be uniquely defined in most cases. This allows to compute a one-to-one Hough transform, every point in the image space voting for one unique point in the parameter space. Moreover, those parameters can be directly estimated on the greyscale image without the need to calculate the contour and without reducing the spatial support of the Hough transform, i.e. densely on the whole image. The general framework using multiscale derivatives is presented, and the one-to-one Hough dense transforms for detecting lines and circles are evaluated and compared with other variants of Hough transforms, from qualitative and computational points of view.