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.

/pdf/deep-residual-learning-for-image-recognition-b75jg61qrq.pdf

Deep Residual Learning for Image Recognition

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

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.

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.

/pdf/going-deeper-with-convolutions-1yobw2o2ds.pdf

Going deeper with convolutions

Up to 17% of all motorcycle accidents occur when the rider is maneuvering through a curve and the main cause of curve accidents can be attributed to inappropriate speed and wrong intra-lane position of the motorcycle. Existing curve warning systems lack crucial state estimation components and do not scale well. We propose a new type of road curvature warning system for motorcycles, combining the latest advances in computer vision, optimal control and mapping technologies to alleviate these shortcomings. Our contributes are fourfold: 1) we predict the motorcycle’s intra-lane position using a convolutional neural network (CNN), 2) we predict the motorcycle roll angle using a CNN, 3) we use an upgraded controller model that incorporates road incline for a more realistic model and prediction, 4) we design a scale-able system by utilizing HERE Technologies map database to obtain the accurate road geometry of the future path. In addition, we present two datasets that are used for training and evaluating of our system respectively, both datasets will be made publicly available. We test our system on a diverse set of real world scenarios and present a detailed case-study. We show that our system is able to predict more accurate and safer curve trajectories, and consequently warn and improve the safety for motorcyclists.

/pdf/learning-a-curve-guardian-for-motorcycles-4xt6929hp3.pdf

Learning a Curve Guardian for Motorcycles

Recovering natural illumination from a single Low-Dynamic Range (LDR) image is a challenging task. To remedy this situation we exploit two properties often found in everyday images. First, images rarely show a single material, but rather multiple ones that all reflect the same illumination. However, the appearance of each material is observed only for some surface orientations, not all. Second, parts of the illumination are often directly observed in the background, without being affected by reflection. Typically, this directly observed part of the illumination is even smaller. We propose a deep Convolutional Neural Network (CNN) that combines prior knowledge about the statistics of illumination and reflectance with an input that makes explicit use of these two observations. Our approach maps multiple partial LDR material observations represented as reflectance maps and a background image to a spherical High-Dynamic Range (HDR) illumination map. For training and testing we propose a new data set comprising of synthetic and real images with multiple materials observed under the same illumination. Qualitative and quantitative evidence shows how both multi-material and using a background are essential to improve illumination estimations.

Natural Illumination from Multiple Materials Using Deep Learning

Event recognition in still images is an intriguing problem and has potential for real applications. This paper addresses the problem of event recognition by proposing a convolutional neural network that exploits knowledge of objects and scenes for event classification (OS2E-CNN). Intuitively, it stands to reason that there exists a correlation among the concepts of objects, scenes, and events. We empirically demonstrate that the recognition of objects and scenes substantially contributes to the recognition of events. Meanwhile, we propose an iterative selection method to identify a subset of object and scene classes, which help to more efficiently and effectively transfer their deep representations to event recognition. Specifically, we develop three types of transferring techniques: (1) initialization-based transferring, (2) knowledge-based transferring, and (3) data-based transferring. These newly designed transferring techniques exploit multi-task learning frameworks to incorporate extra knowledge from other networks and additional datasets into the training procedure of event CNNs. These multi-task learning frameworks turn out to be effective in reducing the effect of over-fitting and improving the generalization ability of the learned CNNs. With OS2E-CNN, we design a multi-ratio and multi-scale cropping strategy, and propose an end-to-end event recognition pipeline. We perform experiments on three event recognition benchmarks: the ChaLearn Cultural Event Recognition dataset, the Web Image Dataset for Event Recognition (WIDER), and the UIUC Sports Event dataset. The experimental results show that our proposed algorithm successfully adapts object and scene representations towards the event dataset and that it achieves the current state-of-the-art performance on these challenging datasets.

Transferring Object-Scene Convolutional Neural Networks for Event Recognition in Still Images.

Increasingly, realistic object, scene, and event modeling is based on image data rather than manual synthesis The paper describes a system for visits to a virtual, 3D archeological site One can navigate through this environment, with a virtual guide as companion One can ask questions using natural, fluent speech The guide will respond and will bring the visitor to the desired place Simple answers are given as changes in the orientations of his head, by him raising his eyebrows or by head nodding In the near future the head will speak

/pdf/image-based-3d-modeling-modeling-from-reality-263p7l4tlk.pdf

Image-based 3D modeling: modeling from reality

The key challenge in learning dense correspondences lies in the lack of ground-truth matches for real image pairs. While photometric consistency losses provide unsupervised alternatives, they struggle with large appearance changes, which are ubiquitous in geometric and semantic matching tasks. Moreover, methods relying on synthetic training pairs often suffer from poor generalisation to real data. 
We propose Warp Consistency, an unsupervised learning objective for dense correspondence regression. Our objective is effective even in settings with large appearance and view-point changes. Given a pair of real images, we first construct an image triplet by applying a randomly sampled warp to one of the original images. We derive and analyze all flow-consistency constraints arising between the triplet. From our observations and empirical results, we design a general unsupervised objective employing two of the derived constraints. We validate our warp consistency loss by training three recent dense correspondence networks for the geometric and semantic matching tasks. Our approach sets a new state-of-the-art on several challenging benchmarks, including MegaDepth, RobotCar and TSS. Code and models are at this http URL.

Luc Van Gool

Papers

Learning a Curve Guardian for Motorcycles

Natural Illumination from Multiple Materials Using Deep Learning

Transferring Object-Scene Convolutional Neural Networks for Event Recognition in Still Images.

Image-based 3D modeling: modeling from reality

Warp Consistency for Unsupervised Learning of Dense Correspondences