Luc Van Gool

Bio: Luc Van Gool is an academic researcher from Katholieke Universiteit Leuven. The author has contributed to research in topics: Computer science & Object detection. The author has an hindex of 133, co-authored 1307 publications receiving 107743 citations. Previous affiliations of Luc Van Gool include Microsoft & ETH Zurich.

Iterative Nearest Neighbors for classification and dimensionality reduction

Abstract: Representative data in terms of a set of selected samples is of interest for various machine learning applications, e.g. dimensionality reduction and classification. The best-known techniques probably still are k-Nearest Neighbors (kNN) and its variants. Recently, richer representations have become popular. Examples are methods based on l 1 -regularized least squares (Sparse Representation (SR)) or l 2 -regularized least squares (Collaborative Representation (CR)), or on l 1 -constrained least squares (Local Linear Embedding (LLE)). We propose Iterative Nearest Neighbors (INN). This is a novel sparse representation that combines the power of SR and LLE with the computational simplicity of kNN. We test our method in terms of dimensionality reduction and classification, using standard benchmarks such as faces (AR), traffic signs (GTSRB), and PASCAL VOC 2007. INN performs better than NN and comparable with CR and SR, while being orders of magnitude faster than the latter.

Parametric stereo for multi-pose face recognition and 3d-face modeling

Abstract: This paper presents a new method for face modeling and face recognition from a pair of calibrated stereo cameras. In a first step, the algorithm builds a stereo reconstruction of the face by adjusting the global transformation parameters and the shape parameters of a 3D morphable face model. The adjustment of the parameters is such that stereo correspondence between both images is established, i.e. such that the 3D-vertices of the model project on similarly colored pixels in both images. In a second step, the texture information is extracted from the image pair and represented in the texture space of the morphable face model. The resulting shape and texture coefficients form a person specific feature vector and face recognition is performed by comparing query vectors with stored vectors. To validate our algorithm, an extensive image database was built. It consists of stereo-pairs of 70 subjects. For recognition testing, the subjects were recorded under 6 different head directions, ranging from a frontal to a profile view. The face recognition results are very good, with 100% recognition on frontal views and 97% recognition on half-profile views.

Augmented faces

Abstract: In this paper we present a fully automatic system for face augmentation on mobile devices. A user can point his mobile phone to a person and the system recognizes his or her face. A tracking algorithm overlays information about the identified person on the screen, thereby achieving an augmented reality effect. The tracker is running on the mobile client, while the recognition is running on a server. The database on the server is built by a fully autonomous crawling method, which taps social networks. For this work we collected 300 000 images from Facebook. The social context gained during this social network analysis is also used to improve the face recognition. The complete system runs in real time on a state-of-the-art mobile phone and is fully automatic, from offline crawling up to augmentation on the mobile device. It can be used to display more information about the identified persons or as a user interface for mixed reality application. To the best of our knowledge this is the first work, which covers such a system end-to-end.

CARN: Convolutional Anchored Regression Network for Fast and Accurate Single Image Super-Resolution

Abstract: Although the accuracy of super-resolution (SR) methods based on convolutional neural networks (CNN) soars high, the complexity and computation also explode with the increased depth and width of the network. Thus, we propose the convolutional anchored regression network (CARN) for fast and accurate single image super-resolution (SISR). Inspired by locally linear regression methods (A+ and ARN), the new architecture consists of regression blocks that map input features from one feature space to another. Different from A+ and ARN, CARN is no longer relying on or limited by hand-crafted features. Instead, it is an end-to-end design where all the operations are converted to convolutions so that the key concepts, i.e., features, anchors, and regressors, are learned jointly. The experiments show that CARN achieves the best speed and accuracy trade-off among the SR methods. The code is available at https://github.com/ofsoundof/CARN.

Deep Residual Learning for Image Recognition

Abstract: Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers—8× deeper than VGG nets [40] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions1, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

Very Deep Convolutional Networks for Large-Scale Image Recognition

Abstract: In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.

Very Deep Convolutional Networks for Large-Scale Image Recognition

Abstract: In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.

Deep Residual Learning for Image Recognition

Abstract: Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers---8x deeper than VGG nets but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

Going deeper with convolutions

Abstract: We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.