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

In this paper, we demonstrate a system that automates the process of recording video lectures in classrooms. Through special hardware (lecturer and audience facing cameras and microphone arrays), we record multiple points of view of the lecture. Person detection and tracking, along with recognition of different human actions are used to digitally zoom in on the lecturer, and alternate focus between the lecturer and the slides or the blackboard. Audio sound source localization, along with face detection and tracking, is used to detect questions from the audience, to digitally zoom in on the member of the audience asking the question and to improve the quality of the sound recording. Finally, an automatic video editing system is used to naturally switch between the different video streams and to compose a compelling end product. We demonstrate the working system in two classrooms, over two 2-h lectures, given by two lecturers.

The CAMETRON Lecture Recording System: High Quality Video Recording and Editing with Minimal Human Supervision

A stereo rig can be calibrated using a calibration grid, but recent work demonstrated the possibility of auto-calibration. There remain two important limitations, however. First, the focal lengths of the cameras should remain fixed, thereby excluding zooming or focusing. Second, the stereo rig must not purely translate, which however is the most natural type of motion. This also implies that these methods collapse when the motion comes close to being a translation.

Euclidean 3D Reconstruction from Stereo Sequences with Variable Focal Lengths

Systems of coupled, non-linear diffusion equations are proposed as a computational tool for grouping. Grouping tasks are divided into two classes - local and bilocal - and for each a prototypical set of equations is presented. It is shown how different cues can be used for grouping given these two blueprints plus cue-specific specialisations. Results are shown for intensity, texture orientation, stereo disparity, optical flow, mirror symmetry, and regular textures. The proposed equations are particularly well suited for parallel implementations. They also show some interesting analogies with basic architectural characteristics of the cortex.

Grouping Based on Coupled Diffusion Maps

3D modeling and registration under wide baseline conditions

Shadow removal is an important computer vision task aiming at the detection and successful removal of the shadow produced by an occluded light source and a photo-realistic restoration of the image contents. Decades of re-search produced a multitude of hand-crafted restoration techniques and, more recently, learned solutions from shad-owed and shadow-free training image pairs. In this work,we propose an unsupervised single image shadow removal solution via self-supervised learning by using a conditioned mask. In contrast to existing literature, we do not require paired shadowed and shadow-free images, instead we rely on self-supervision and jointly learn deep models to remove and add shadows to images. We validate our approach on the recently introduced ISTD and USR datasets. We largely improve quantitatively and qualitatively over the compared methods and set a new state-of-the-art performance in single image shadow removal.

Luc Van Gool

Papers

The CAMETRON Lecture Recording System: High Quality Video Recording and Editing with Minimal Human Supervision

Euclidean 3D Reconstruction from Stereo Sequences with Variable Focal Lengths

Grouping Based on Coupled Diffusion Maps

3D modeling and registration under wide baseline conditions

Self-Supervised Shadow Removal.