663 citations · 775 across the 8 of their papers we have counts for
9 papers
Hyperplane Arrangements of Trained ConvNets Are Biased
Matteo Gamba, Stefan Carlsson, Hossein Azizpour +1
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 h…
Geometry of Deep Convolutional Networks
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 netwo…
Spotlight the Negatives: A Generalized Discriminative Latent Model
Hossein Azizpour, Mostafa Arefiyan, Sobhan Naderi Parizi +1
Discriminative latent variable models (LVM) are frequently applied to various visual recognition tasks. In these systems the latent (hidden) variables provide a formalism for model…
Visual Instance Retrieval with Deep Convolutional Networks
Ali Sharif Razavian, Josephine Sullivan, Stefan Carlsson +1
This paper provides an extensive study on the availability of image representations based on convolutional networks (ConvNets) for the task of visual instance retrieval. Besides th…
Persistent Evidence of Local Image Properties in Generic ConvNets
Ali Sharif Razavian, Hossein Azizpour, Atsuto Maki +3
Supervised training of a convolutional network for object classification should make explicit any information related to the class of objects and disregard any auxiliary informatio…
Factors of Transferability for a Generic ConvNet Representation
Hossein Azizpour, Ali Sharif Razavian, Josephine Sullivan +2
Evidence is mounting that Convolutional Networks (ConvNets) are the most effective representation learning method for visual recognition tasks. In the common scenario, a ConvNet is…
Large Scale, Large Margin Classification using Indefinite Similarity Measures
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 train…
Self-tuned Visual Subclass Learning with Shared Samples An Incremental Approach
Hossein Azizpour, Stefan Carlsson
Computer vision tasks are traditionally defined and evaluated using semantic categories. However, it is known to the field that semantic classes do not necessarily correspond to a…
CNN Features off-the-shelf: an Astounding Baseline for Recognition
Ali Sharif Razavian, Hossein Azizpour, Josephine Sullivan +1
Recent results indicate that the generic descriptors extracted from the convolutional neural networks are very powerful. This paper adds to the mounting evidence that this is indee…