1 code implementation • 17 Mar 2020 • Matteo Gamba, Stefan Carlsson, Hossein Azizpour, Mårten Björkman
We investigate the geometric properties of the functions learned by trained ConvNets in the preactivation space of their convolutional layers, by performing an empirical study of hyperplane arrangements induced by a convolutional layer.
no code implementations • 21 May 2019 • Stefan Carlsson
We give a formal procedure for computing preimages of convolutional network outputs using the dual basis defined from the set of hyperplanes associated with the layers of the network.
no code implementations • 8 Jul 2015 • Hossein Azizpour, Mostafa Arefiyan, Sobhan Naderi Parizi, Stefan Carlsson
Discriminative latent variable models (LVM) are frequently applied to various visual recognition tasks.
no code implementations • 20 Dec 2014 • Ali Sharif Razavian, Josephine Sullivan, Stefan Carlsson, Atsuto Maki
This paper provides an extensive study on the availability of image representations based on convolutional networks (ConvNets) for the task of visual instance retrieval.
no code implementations • 24 Nov 2014 • Ali Sharif Razavian, Hossein Azizpour, Atsuto Maki, Josephine Sullivan, Carl Henrik Ek, Stefan Carlsson
Supervised training of a convolutional network for object classification should make explicit any information related to the class of objects and disregard any auxiliary information associated with the capture of the image or the variation within the object class.
no code implementations • 22 Jun 2014 • Hossein Azizpour, Ali Sharif Razavian, Josephine Sullivan, Atsuto Maki, Stefan Carlsson
In the common scenario, a ConvNet is trained on a large labeled dataset (source) and the feed-forward units activation of the trained network, at a certain layer of the network, is used as a generic representation of an input image for a task with relatively smaller training set (target).
no code implementations • 27 May 2014 • Omid Aghazadeh, Stefan Carlsson
Despite the success of the popular kernelized support vector machines, they have two major limitations: they are restricted to Positive Semi-Definite (PSD) kernels, and their training complexity scales at least quadratically with the size of the data.
no code implementations • 22 May 2014 • Hossein Azizpour, Stefan Carlsson
Finally, we show that state of the art object detection methods (e. g. DPM) are unable to use the tails of this distribution comprising 50\% of the training samples.
4 code implementations • 23 Mar 2014 • Ali Sharif Razavian, Hossein Azizpour, Josephine Sullivan, Stefan Carlsson
We report on a series of experiments conducted for different recognition tasks using the publicly available code and model of the \overfeat network which was trained to perform object classification on ILSVRC13.
no code implementations • CVPR 2013 • Magnus Burenius, Josephine Sullivan, Stefan Carlsson
We consider the problem of automatically estimating the 3D pose of humans from images, taken from multiple calibrated views.