1.1k citations · 4k across the 76 of their papers we have counts for
10 papers · 1 filter
Learning PAC-Bayes Priors for Probabilistic Neural Networks
Maria Perez-Ortiz, Omar Rivasplata, Benjamin Guedj +5
Recent works have investigated deep learning models trained by optimising PAC-Bayes bounds, with priors that are learnt on subsets of the data. This combination has been shown to l…
Differentiable Neural Architecture Learning for Efficient Neural Network Design
Qingbei Guo, Xiao-Jun Wu, Josef Kittler +1
Automated neural network design has received ever-increasing attention with the evolution of deep convolutional neural networks (CNNs), especially involving their deployment on emb…
Self-grouping Convolutional Neural Networks
Qingbei Guo, Xiao-Jun Wu, Josef Kittler +1
Although group convolution operators are increasingly used in deep convolutional neural networks to improve the computational efficiency and to reduce the number of parameters, mos…
Deep Convolutional Neural Network Ensembles using ECOC
Sara Atito Ali Ahmed, Cemre Zor, Berrin Yanikoglu +2
Deep neural networks have enhanced the performance of decision making systems in many applications including image understanding, and further gains can be achieved by constructing…
Multi-Task Kernel Null-Space for One-Class Classification
Shervin Rahimzadeh Arashloo, Josef Kittler
The one-class kernel spectral regression (OC-KSR), the regression-based formulation of the kernel null-space approach has been found to be an effective Fisher criterion-based metho…
Robust One-Class Kernel Spectral Regression
Shervin Rahimzadeh Arashloo, Josef Kittler
The kernel null-space technique and its regression-based formulation (called one-class kernel spectral regression, a.k.a. OC-KSR) is known to be an effective and computationally at…
Discriminative Supervised Hashing for Cross-Modal similarity Search
Jun Yu, Xiao-Jun Wu, Josef Kittler
With the advantage of low storage cost and high retrieval efficiency, hashing techniques have recently been an emerging topic in cross-modal similarity search. As multiple modal da…
Learning Discriminative Hashing Codes for Cross-Modal Retrieval based on Multi-view Features
Jun Yu, Xiao-Jun Wu, Josef Kittler
Hashing techniques have been applied broadly in retrieval tasks due to their low storage requirements and high speed of processing. Many hashing methods based on a single view have…
One-Class Kernel Spectral Regression
Shervin Rahimzadeh Arashloo, Josef Kittler
The paper introduces a new efficient nonlinear one-class classifier formulated as the Rayleigh quotient criterion optimisation. The method, operating in a reproducing kernel Hilber…
Delta divergence: A novel decision cognizant measure of classifier incongruence
Josef Kittler, Cemre Zor
Disagreement between two classifiers regarding the class membership of an observation in pattern recognition can be indicative of an anomaly and its nuance. As in general classifie…