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

Often when we review our holiday photos, we notice things we wish we could have avoided, such as vehicles, construction work, or simply other tourists. We cannot go back and retake the photo, so what can we do if we want to remove these things from our photos? We want to replace these sections of the image in a convincing way, preferably with what would really have been seen there without the occlusions. Previous work on this problem, often referred to as “inpainting”, are mainly applicable to small image regions, and rely largely on models of the local behaviour of natural images, e.g. [3, 5]. Recently, replacing large occlusions in photographs has been approached using images from the Internet [2, 7] or by combining several images captured at approximately the same time [1, 9]. In this paper we leverage recent advances in viewpoint invariant image search [8] to find other images of the same scene on the Internet. Beginning with a query image containing a target region to be replaced, we first use an online image search engine to retrieve images of the same scene, and take these to be a set of oracles. Since these images may have significant variations in viewpoint and lighting, we register each oracle to the query image using multiple homographies and a simple global photometric correction. We then use each oracle to propose a solution, by copying image data into the target region using Poisson blending. Finally, we use a Markov random field (MRF) formulation to combine the proposals into a single, occlusion-free result. Figure 1 shows the main stages of our system, and compares our result to those of two other methods.

/pdf/get-out-of-my-picture-internet-based-inpainting-g5any931cc.pdf

Get Out of my Picture! Internet-based Inpainting.

Our goal is to learn a compact, discriminative vector representation of a face track, suitable for the face recognition tasks of verification and classification. To this end, we propose a novel face track descriptor, based on the Fisher Vector representation, and demonstrate that it has a number of favourable properties. First, the descriptor is suitable for tracks of both frontal and profile faces, and is insensitive to their pose. Second, the descriptor is compact due to discriminative dimensionality reduction, and it can be further compressed using binarization. Third, the descriptor can be computed quickly (using hard quantization) and its compact size and fast computation render it very suitable for large scale visual repositories. Finally, the descriptor demonstrates good generalization when trained on one dataset and tested on another, reflecting its tolerance to the dataset bias. In the experiments we show that the descriptor exceeds the state of the art on both face verification task (YouTube Faces without outside training data, and INRIA-Buffy benchmarks), and face classification task (using the Oxford-Buffy dataset).

/pdf/a-compact-and-discriminative-face-track-descriptor-3we3zuunsb.pdf

A Compact and Discriminative Face Track Descriptor

The objective of this paper is to improve large scale visual object retrieval for visual place recognition. Geo-localization based on a visual query is made difficult by plenty of non-distinctive features which commonly occur in imagery of urban environments, such as generic modern windows, doors, cars, trees, etc. The focus of this work is to adapt standard Hamming Embedding retrieval system to account for varying descriptor distinctiveness. To this end, we propose a novel method for efficiently estimating distinctiveness of all database descriptors, based on estimating local descriptor density everywhere in the descriptor space. In contrast to all competing methods, the (unsupervised) training time for our method (DisLoc) is linear in the number database descriptors and takes only a 100 s on a single CPU core for a 1 million image database. Furthermore, the added memory requirements are negligible (1 %).

/pdf/dislocation-scalable-descriptor-distinctiveness-for-location-1d4tepb8l2.pdf

DisLocation: Scalable Descriptor Distinctiveness for Location Recognition

A number of recent papers have argued that invariants do not exist for three-dimensional point sets in general position, which has often been misinterpreted to mean that invariants cannot be computed for any three-dimensional structure. It is proved by example that although the general statement is true, invariants do exist for structured three-dimensional point sets. Projective invariants are derived for two object classes: the first is for points that lie on the vertices of polyhedra, and the second for objects that are projectively equivalent to ones possessing a bilateral symmetry. The motivations for computing such invariants are twofold: they can be used for recognition, and they can be used to compute projective structure. Examples of invariants computed from real images are given. >

Extracting projective structure from single perspective views of 3D point sets

We describe a method for generating a video of a talking face. The method takes still images of the target face and an audio speech segment as inputs, and generates a video of the target face lip synched with the audio. The method runs in real time and is applicable to faces and audio not seen at training time. To achieve this we develop an encoder–decoder convolutional neural network (CNN) model that uses a joint embedding of the face and audio to generate synthesised talking face video frames. The model is trained on unlabelled videos using cross-modal self-supervision. We also propose methods to re-dub videos by visually blending the generated face into the source video frame using a multi-stream CNN model.

/pdf/you-said-that-synthesising-talking-faces-from-audio-1m77jd8oka.pdf

Andrew Zisserman

Papers

Get Out of my Picture! Internet-based Inpainting.

A Compact and Discriminative Face Track Descriptor

DisLocation: Scalable Descriptor Distinctiveness for Location Recognition

Extracting projective structure from single perspective views of 3D point sets

You Said That?: Synthesising Talking Faces from Audio