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

The explosion of image data on the Internet has the potential to foster more sophisticated and robust models and algorithms to index, retrieve, organize and interact with images and multimedia data. But exactly how such data can be harnessed and organized remains a critical problem. We introduce here a new database called “ImageNet”, a large-scale ontology of images built upon the backbone of the WordNet structure. ImageNet aims to populate the majority of the 80,000 synsets of WordNet with an average of 500-1000 clean and full resolution images. This will result in tens of millions of annotated images organized by the semantic hierarchy of WordNet. This paper offers a detailed analysis of ImageNet in its current state: 12 subtrees with 5247 synsets and 3.2 million images in total. We show that ImageNet is much larger in scale and diversity and much more accurate than the current image datasets. Constructing such a large-scale database is a challenging task. We describe the data collection scheme with Amazon Mechanical Turk. Lastly, we illustrate the usefulness of ImageNet through three simple applications in object recognition, image classification and automatic object clustering. We hope that the scale, accuracy, diversity and hierarchical structure of ImageNet can offer unparalleled opportunities to researchers in the computer vision community and beyond.

/pdf/imagenet-a-large-scale-hierarchical-image-database-1e8f663s1h.pdf

ImageNet: A large-scale hierarchical image database

There is large consent that successful training of deep networks requires many thousand annotated training samples. In this paper, we present a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently. The architecture consists of a contracting path to capture context and a symmetric expanding path that enables precise localization. We show that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. Using the same network trained on transmitted light microscopy images (phase contrast and DIC) we won the ISBI cell tracking challenge 2015 in these categories by a large margin. Moreover, the network is fast. Segmentation of a 512x512 image takes less than a second on a recent GPU. The full implementation (based on Caffe) and the trained networks are available at http://lmb.informatik.uni-freiburg.de/people/ronneber/u-net .

/pdf/u-net-convolutional-networks-for-biomedical-image-2xoyjzggxv.pdf

U-Net: Convolutional Networks for Biomedical Image Segmentation

We describe how 3D affine measurements may be computed from a single perspective view of a scene given only minimal geometric information determined from the image. This minimal information is typically the vanishing line of a reference plane and a vanishing point for a direction not parallel to the plane. It is shown that affine scene structure may then be determined from the image, without knowledge of the camera's internal calibration (e.g. focal length), nor of the explicit relation between camera and world (pose). In particular we show how to: compute the distance between planes parallel to the reference plane (up to a common scale factor); compute area and length ratios on any plane parallel to the reference plane; determine the camera's (viewer's) location. Simple geometric derivations are given for these results. We also develop an algebraic representation which unifies the three types of measurement and, amongst other advantages, permits a first order error propagation analysis to be performed, associating an uncertainty with each measurement. We demonstrate the technique for a variety of applications, including height measurements in forensic images and 3D graphical modelling from single images.

/pdf/single-view-metrology-4b47v84cbh.pdf

Single view metrology

The objective of this work is to find objects in paintings by learning object-category classifiers from available sources of natural images. Finding such objects is of much benefit to the art history community as well as being a challenging problem in large-scale retrieval and domain adaptation.

In Search of Art

Describes a method to determine affine and metric calibration for a stereo rig. The method does not involve the use of calibration objects or special motions, but simply a single general motion of the rig with fixed parameters (i.e. camera parameters and relative orientation of the camera pair). The novel aspects of this work are: first, relating the distinguished objects of Euclidean geometry to fixed entities of a Euclidean transformation matrix; second, showing that these fixed entities are accessible from the conjugate Euclidean transformation arising from the projective transformation of the structure under a motion of the fixed stereo rig; and third, a robust and automatic implementation of the method. Results are included of affine and metric calibration and structure recovery using images of real scenes.

Metric calibration of a stereo rig

A structure from motion algorithm is described which recovers structure and camera position, modulo a projective ambiguity. Camera calibration is not required, and camera parameters such as focal length can be altered freely during motion. Unlike recent schemes which compute projective or affine structure using a batch process, the structure is updated sequentially over an image sequence. A specialisation of the algorithm to recover structure modulo an affine transformation is described. We demonstrate how the affine coordinate frame can be periodically updated to prevent drift over time.

/pdf/navigation-using-affine-structure-from-motion-b3xibrotpz.pdf

Navigation using Affine Structure from Motion

Investigation of the automation of radiological features from magnetic resonance images (MRIs) of the lumbar spine. To automate the process of grading lumbar intervertebral discs and vertebral bodies from MRIs. MR imaging is the most common imaging technique used in investigating low back pain (LBP). Various features of degradation, based on MRIs, are commonly recorded and graded, e.g., Modic change and Pfirrmann grading of intervertebral discs. Consistent scoring and grading is important for developing robust clinical systems and research. Automation facilitates this consistency and reduces the time of radiological analysis considerably and hence the expense. 12,018 intervertebral discs, from 2009 patients, were graded by a radiologist and were then used to train: (1) a system to detect and label vertebrae and discs in a given scan, and (2) a convolutional neural network (CNN) model that predicts several radiological gradings. The performance of the model, in terms of class average accuracy, was compared with the intra-observer class average accuracy of the radiologist. The detection system achieved 95.6% accuracy in terms of disc detection and labeling. The model is able to produce predictions of multiple pathological gradings that consistently matched those of the radiologist. The model identifies ‘Evidence Hotspots’ that are the voxels that most contribute to the degradation scores. Automation of radiological grading is now on par with human performance. The system can be beneficial in aiding clinical diagnoses in terms of objectivity of gradings and the speed of analysis. It can also draw the attention of a radiologist to regions of degradation. This objectivity and speed is an important stepping stone in the investigation of the relationship between MRIs and clinical diagnoses of back pain in large cohorts. Level of Evidence: Level 3.

/pdf/issls-prize-in-bioengineering-science-2017-automation-of-3todndjmh1.pdf

ISSLS PRIZE IN BIOENGINEERING SCIENCE 2017: Automation of reading of radiological features from magnetic resonance images (MRIs) of the lumbar spine without human intervention is comparable with an expert radiologist.

Andrew Zisserman

Papers

Single view metrology

In Search of Art

Metric calibration of a stereo rig

Navigation using Affine Structure from Motion

ISSLS PRIZE IN BIOENGINEERING SCIENCE 2017: Automation of reading of radiological features from magnetic resonance images (MRIs) of the lumbar spine without human intervention is comparable with an expert radiologist.