The Experts below are selected from a list of 117 Experts worldwide ranked by ideXlab platform
Tinne Tuytelaars - One of the best experts on this subject based on the ideXlab platform.
-
ECCV Workshops (3) - Lightweight Unsupervised Domain Adaptation by Convolutional Filter Reconstruction
Lecture Notes in Computer Science, 2016Co-Authors: Rahaf Aljundi, Tinne TuytelaarsAbstract:Recently proposed domain adaptation methods retrain the network parameters and overcome the domain shift issue to a large extent. However, this requires access to all (labeled) source data, a large amount of (unlabeled) target data, and plenty of computational resources. In this work, we propose a lightweight alternative, that allows adapting to the target domain based on a limited number of target samples in a matter of minutes. To this end, we first analyze the output of each Convolutional layer from a domain adaptation perspective. Surprisingly, we find that already at the very first layer, domain shift effects pop up. We then propose a new domain adaptation method, where first layer Convolutional Filters that are badly affected by the domain shift are reconstructed based on less affected ones.
-
lightweight unsupervised domain adaptation by Convolutional Filter reconstruction
European Conference on Computer Vision, 2016Co-Authors: Rahaf Aljundi, Tinne TuytelaarsAbstract:Recently proposed domain adaptation methods retrain the network parameters and overcome the domain shift issue to a large extent. However, this requires access to all (labeled) source data, a large amount of (unlabeled) target data, and plenty of computational resources. In this work, we propose a lightweight alternative, that allows adapting to the target domain based on a limited number of target samples in a matter of minutes. To this end, we first analyze the output of each Convolutional layer from a domain adaptation perspective. Surprisingly, we find that already at the very first layer, domain shift effects pop up. We then propose a new domain adaptation method, where first layer Convolutional Filters that are badly affected by the domain shift are reconstructed based on less affected ones.
-
Lightweight Unsupervised Domain Adaptation by Convolutional Filter Reconstruction
arXiv: Computer Vision and Pattern Recognition, 2016Co-Authors: Rahaf Aljundi, Tinne TuytelaarsAbstract:End-to-end learning methods have achieved impressive results in many areas of computer vision. At the same time, these methods still suffer from a degradation in performance when testing on new datasets that stem from a different distribution. This is known as the domain shift effect. Recently proposed adaptation methods focus on retraining the network parameters. However, this requires access to all (labeled) source data, a large amount of (unlabeled) target data, and plenty of computational resources. In this work, we propose a lightweight alternative, that allows adapting to the target domain based on a limited number of target samples in a matter of minutes rather than hours, days or even weeks. To this end, we first analyze the output of each Convolutional layer from a domain adaptation perspective. Surprisingly, we find that already at the very first layer, domain shift effects pop up. We then propose a new domain adaptation method, where first layer Convolutional Filters that are badly affected by the domain shift are reconstructed based on less affected ones. This improves the performance of the deep network on various benchmark datasets.
Rahaf Aljundi - One of the best experts on this subject based on the ideXlab platform.
-
ECCV Workshops (3) - Lightweight Unsupervised Domain Adaptation by Convolutional Filter Reconstruction
Lecture Notes in Computer Science, 2016Co-Authors: Rahaf Aljundi, Tinne TuytelaarsAbstract:Recently proposed domain adaptation methods retrain the network parameters and overcome the domain shift issue to a large extent. However, this requires access to all (labeled) source data, a large amount of (unlabeled) target data, and plenty of computational resources. In this work, we propose a lightweight alternative, that allows adapting to the target domain based on a limited number of target samples in a matter of minutes. To this end, we first analyze the output of each Convolutional layer from a domain adaptation perspective. Surprisingly, we find that already at the very first layer, domain shift effects pop up. We then propose a new domain adaptation method, where first layer Convolutional Filters that are badly affected by the domain shift are reconstructed based on less affected ones.
-
lightweight unsupervised domain adaptation by Convolutional Filter reconstruction
European Conference on Computer Vision, 2016Co-Authors: Rahaf Aljundi, Tinne TuytelaarsAbstract:Recently proposed domain adaptation methods retrain the network parameters and overcome the domain shift issue to a large extent. However, this requires access to all (labeled) source data, a large amount of (unlabeled) target data, and plenty of computational resources. In this work, we propose a lightweight alternative, that allows adapting to the target domain based on a limited number of target samples in a matter of minutes. To this end, we first analyze the output of each Convolutional layer from a domain adaptation perspective. Surprisingly, we find that already at the very first layer, domain shift effects pop up. We then propose a new domain adaptation method, where first layer Convolutional Filters that are badly affected by the domain shift are reconstructed based on less affected ones.
-
Lightweight Unsupervised Domain Adaptation by Convolutional Filter Reconstruction
arXiv: Computer Vision and Pattern Recognition, 2016Co-Authors: Rahaf Aljundi, Tinne TuytelaarsAbstract:End-to-end learning methods have achieved impressive results in many areas of computer vision. At the same time, these methods still suffer from a degradation in performance when testing on new datasets that stem from a different distribution. This is known as the domain shift effect. Recently proposed adaptation methods focus on retraining the network parameters. However, this requires access to all (labeled) source data, a large amount of (unlabeled) target data, and plenty of computational resources. In this work, we propose a lightweight alternative, that allows adapting to the target domain based on a limited number of target samples in a matter of minutes rather than hours, days or even weeks. To this end, we first analyze the output of each Convolutional layer from a domain adaptation perspective. Surprisingly, we find that already at the very first layer, domain shift effects pop up. We then propose a new domain adaptation method, where first layer Convolutional Filters that are badly affected by the domain shift are reconstructed based on less affected ones. This improves the performance of the deep network on various benchmark datasets.
Alejandro F. Frangi - One of the best experts on this subject based on the ideXlab platform.
-
MICCAI (3) - DOTE: Dual Convolutional Filter lEarning for Super-Resolution and Cross-Modality Synthesis in MRI
Medical Image Computing and Computer Assisted Intervention − MICCAI 2017, 2017Co-Authors: Yawen Huang, Ling Shao, Alejandro F. FrangiAbstract:Cross-modal image synthesis is a topical problem in medical image computing. Existing methods for image synthesis are either tailored to a specific application, require large scale training sets, or are based on partitioning images into overlapping patches. In this paper, we propose a novel Dual Convolutional Filter lEarning (DOTE) approach to overcome the drawbacks of these approaches. We construct a closed loop joint Filter learning strategy that generates informative feedback for model self-optimization. Our method can leverage data more efficiently thus reducing the size of the required training set. We extensively evaluate DOTE in two challenging tasks: image super-resolution and cross-modality synthesis. The experimental results demonstrate superior performance of our method over other state-of-the-art methods.
-
DOTE: Dual Convolutional Filter lEarning for Super-Resolution and Cross-Modality Synthesis in MRI
arXiv: Computer Vision and Pattern Recognition, 2017Co-Authors: Yawen Huang, Ling Shao, Alejandro F. FrangiAbstract:Cross-modal image synthesis is a topical problem in medical image computing. Existing methods for image synthesis are either tailored to a specific application, require large scale training sets, or are based on partitioning images into overlapping patches. In this paper, we propose a novel Dual Convolutional Filter lEarning (DOTE) approach to overcome the drawbacks of these approaches. We construct a closed loop joint Filter learning strategy that generates informative feedback for model self-optimization. Our method can leverage data more efficiently thus reducing the size of the required training set. We extensively evaluate DOTE in two challenging tasks: image super-resolution and cross-modality synthesis. The experimental results demonstrate superior performance of our method over other state-of-the-art methods.
Stefan Wessel - One of the best experts on this subject based on the ideXlab platform.
-
parameter diagnostics of phases and phase transition learning by neural networks
Physical Review B, 2018Co-Authors: Philippe Suchsland, Stefan WesselAbstract:We present an analysis of neural network-based machine learning schemes for phases and phase transitions in theoretical condensed matter research, focusing on neural networks with a single hidden layer. Such shallow neural networks were previously found to be efficient in classifying phases and locating phase transitions of various basic model systems. In order to rationalize the emergence of the classification process and for identifying any underlying physical quantities, it is feasible to examine the weight matrices and the Convolutional Filter kernels that result from the learning process of such shallow networks. Furthermore, we demonstrate how the learning-by-confusing scheme can be used, in combination with a simple threshold-value classification method, to diagnose the learning parameters of neural networks. In particular, we study the classification process of both fully-connected and Convolutional neural networks for the two-dimensional Ising model with extended domain wall configurations included in the low-temperature regime. Moreover, we consider the two-dimensional XY model and contrast the performance of the learning-by-confusing scheme and Convolutional neural networks trained on bare spin configurations to the case of preprocessed samples with respect to vortex configurations. We discuss these findings in relation to similar recent investigations and possible further applications.
Yawen Huang - One of the best experts on this subject based on the ideXlab platform.
-
MICCAI (3) - DOTE: Dual Convolutional Filter lEarning for Super-Resolution and Cross-Modality Synthesis in MRI
Medical Image Computing and Computer Assisted Intervention − MICCAI 2017, 2017Co-Authors: Yawen Huang, Ling Shao, Alejandro F. FrangiAbstract:Cross-modal image synthesis is a topical problem in medical image computing. Existing methods for image synthesis are either tailored to a specific application, require large scale training sets, or are based on partitioning images into overlapping patches. In this paper, we propose a novel Dual Convolutional Filter lEarning (DOTE) approach to overcome the drawbacks of these approaches. We construct a closed loop joint Filter learning strategy that generates informative feedback for model self-optimization. Our method can leverage data more efficiently thus reducing the size of the required training set. We extensively evaluate DOTE in two challenging tasks: image super-resolution and cross-modality synthesis. The experimental results demonstrate superior performance of our method over other state-of-the-art methods.
-
DOTE: Dual Convolutional Filter lEarning for Super-Resolution and Cross-Modality Synthesis in MRI
arXiv: Computer Vision and Pattern Recognition, 2017Co-Authors: Yawen Huang, Ling Shao, Alejandro F. FrangiAbstract:Cross-modal image synthesis is a topical problem in medical image computing. Existing methods for image synthesis are either tailored to a specific application, require large scale training sets, or are based on partitioning images into overlapping patches. In this paper, we propose a novel Dual Convolutional Filter lEarning (DOTE) approach to overcome the drawbacks of these approaches. We construct a closed loop joint Filter learning strategy that generates informative feedback for model self-optimization. Our method can leverage data more efficiently thus reducing the size of the required training set. We extensively evaluate DOTE in two challenging tasks: image super-resolution and cross-modality synthesis. The experimental results demonstrate superior performance of our method over other state-of-the-art methods.