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

Affine reconstruction from perspective image pairs

The feature correlation layer serves as a key neural network module in numerous computer vision problems that involve dense correspondences between image pairs. It predicts a correspondence volume by evaluating dense scalar products between feature vectors extracted from pairs of locations in two images. However, this point-to-point feature comparison is insufficient when disambiguating multiple similar regions in an image, severely affecting the performance of the end task. We propose GOCor, a fully differentiable dense matching module, acting as a direct replacement to the feature correlation layer. The correspondence volume generated by our module is the result of an internal optimization procedure that explicitly accounts for similar regions in the scene. Moreover, our approach is capable of effectively learning spatial matching priors to resolve further matching ambiguities. We analyze our GOCor module in extensive ablative experiments. When integrated into state-of-the-art networks, our approach significantly outperforms the feature correlation layer for the tasks of geometric matching, optical flow, and dense semantic matching. The code and trained models will be made available at this http URL.

/pdf/gocor-bringing-globally-optimized-correspondence-volumes-1x7cpvm11x.pdf

GOCor: Bringing Globally Optimized Correspondence Volumes into Your Neural Network

Despite the great advances made in the field of image super-resolution (ISR) during the last years, the performance has merely been evaluated perceptually. Thus, it is still unclear whether ISR is helpful for other vision tasks. In this paper, we present the first comprehensive study and analysis of the usefulness of ISR for other vision applications. In particular, six ISR methods are evaluated on four popular vision tasks, namely edge detection, semantic image segmentation, digit recognition, and scene recognition. We show that applying ISR to input images of other vision systems does improve their performance when the input images are of low-resolution. We also study the correlation between four standard perceptual evaluation criteria (namely PSNR, SSIM, IFC, and NQM) and the usefulness of ISR to the vision tasks. Experiments show that they correlate well with each other in general, but perceptual criteria are still not accurate enough to be used as full proxies for the usefulness. We hope this work will inspire the community to evaluate ISR methods also in real vision applications, and to adopt ISR as a pre-processing step of other vision tasks if the resolution of their input images is low.

Is image super-resolution helpful for other vision tasks?

In this paper, we address the problem of 3D articulated multi-person tracking in busy street scenes from a moving, human-level observer. In order to handle the complexity of multi-person interactions, we propose to pursue a two-stage strategy. A multi-body detection-based tracker first analyzes the scene and recovers individual pedestrian trajectories, bridging sensor gaps and resolving temporary occlusions. A specialized articulated tracker is then applied to each recovered pedestrian trajectory in parallel to estimate the tracked person's precise body pose over time. This articulated tracker is implemented in a Gaussian Process framework and operates on global pedestrian silhouettes using a learned statistical representation of human body dynamics. We interface the two tracking levels through a guided segmentation stage, which combines traditional bottom-up cues with top-down information from a human detector and the articulated tracker's shape prediction. We show the proposed approach's viability and demonstrate its performance for articulated multi-person tracking on several challenging video sequences of a busy inner-city scenario.

Articulated Multi-body Tracking under Egomotion

Consensus maximization has proven to be a useful tool for robust estimation. While randomized methods like RANSAC are fast, they do not guarantee global optimality and fail to manage large amounts of outliers. On the other hand, global methods are commonly slow because they do not exploit the structure of the problem at hand. In this paper, we show that the solution space can be reduced by introducing Linear Matrix Inequality (LMI) constraints. This leads to significant speed ups of the optimization time even for large amounts of outliers, while maintaining global optimality. We study several cases in which the objective variables have a special structure, such as rotation, scaled-rotation, and essential matrices, which are posed as LMI constraints. This is very useful in several standard computer vision problems, such as estimating Similarity Transformations, Absolute Poses, and Relative Poses, for which we obtain compelling results on both synthetic and real datasets. With up to 90 percent outlier rate, where RANSAC often fails, our constrained approach is consistently faster than the non-constrained one - while finding the same global solution.

/pdf/consensus-maximization-with-linear-matrix-inequality-1ubunsi2rb.pdf

Luc Van Gool

Papers

Affine reconstruction from perspective image pairs

GOCor: Bringing Globally Optimized Correspondence Volumes into Your Neural Network

Is image super-resolution helpful for other vision tasks?

Articulated Multi-body Tracking under Egomotion

Consensus Maximization with Linear Matrix Inequality Constraints