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.

Weakly Supervised Object Discovery by Generative Adversarial & Ranking Networks

Abstract: The deep generative adversarial networks (GAN) recently have been shown to be promising for different computer vision applications, like image editing, synthesizing high resolution images, generating videos, etc. These networks and the corresponding learning scheme can handle various visual space mappings. We approach GANs with a novel training method and learning objective, to discover multiple object instances for three cases: 1) synthesizing a picture of a specific object within a cluttered scene; 2) localizing different categories in images for weakly supervised object detection; and 3) improving object discovery in object detection pipelines. A crucial advantage of our method is that it learns a new deep similarity metric, to distinguish multiple objects in one image. We demonstrate that the network can act as an encoder-decoder generating parts of an image which contain an object, or as a modified deep CNN to represent images for object detection in supervised and weakly supervised scheme. Our ranking GAN offers a novel way to search through images for object specific patterns. We have conducted experiments for different scenarios and demonstrate the method performance for object synthesizing and weakly supervised object detection and classification using the MS-COCO and PASCAL VOC datasets.

3D Saliency for Finding Landmark Buildings

Abstract: In urban environments the most interesting and effective factors for localization and navigation are landmark buildings. This paper proposes a novel method to detect such buildings that stand out, i.e. would be given the status of 'landmark'. The method works in a fully unsupervised way, i.e. it can be applied to different cities without requiring annotation. First, salient points are detected, based on the analysis of their features as well as those found in their spatial neighborhood. Second, learning refines the points by finding connected landmark components and training a classifier to distinguish these from common building components. Third, landmark components are aggregated into complete landmark buildings. Experiments on city-scale point clouds show the viability and efficiency of our approach on various tasks.

Total recall : a plea for realism in models of the past

Abstract: Computer technologies make possible virtual reconstructions of ancient structures. In this paper we give a concise overview of the techniques we have used to build a detailed 3D model of the Antonine nymphaeum at the Sagalassos excavation site. These include techniques for 3D acquisition, texture modelling and synthesis, data clean-up, and visualisation. Our aim has been to build a maximally realistic but also veridical model. The paper is also meant as a plea to include such levels of detail into models where the data allow it. There is an ongoing debate whether high levels of detail, and photo-realistic visualisation for that matter, are desirable in the first place. Indeed, detailed models combined with photo-realistic rendering may convey an impression of reality, whereas they can never represent the situation like it really was. Of course, we agree that filling in completely hypothetical structures may be more misleading than it is informative. On the other hand, often good indications about these structures, or even actual fragments thereof, may be available. Leaving out any structures one is not absolutely sure about, combining basic geometric primitives, or adopting copy-and-paste methods – all aspects regularly found with simple model building – also entail dangers. Such models may fail to generate interest with the public and also if they do, may fail to illustrate ornamental sophistication or shape and pattern irregularities. * Corresponding author.

Multi-view stereo and LiDAR for outdoor scene modelling

Abstract: In this paper we want to start the discussion on whether image based 3-D modelling techniques and especially multi-view stereo can possibly be used to replace LIDAR systems for outdoor 3D data acquisition. Two main issues have to be addressed in this context: (i) camera self-calibration and (ii) dense multi-view depth estimation. To investigate both, we have acquired test data from outdoor scenes with LIDAR and cameras. Using the LIDAR data as reference we provide an evaluation procedure to these two major parts of the 3D model building pipeline. The test images are available for the community as benchmark data.

Latent hough transform for object detection

Abstract: Hough transform based methods for object detection work by allowing image features to vote for the location of the object. While this representation allows for parts observed in different training instances to support a single object hypothesis, it also produces false positives by accumulating votes that are consistent in location but inconsistent in other properties like pose, color, shape or type. In this work, we propose to augment the Hough transform with latent variables in order to enforce consistency among votes. To this end, only votes that agree on the assignment of the latent variable are allowed to support a single hypothesis. For training a Latent Hough Transform (LHT) model, we propose a learning scheme that exploits the linearity of the Hough transform based methods. Our experiments on two datasets including the challenging PASCAL VOC 2007 benchmark show that our method outperforms traditional Hough transform based methods leading to state-of-the-art performance on some categories.

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.