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

In this chapter we discuss modeling and removing spatially-variant blur from photographs. We describe a compact global parameterization of camera shake blur, based on the 3D rotation of the camera during the exposure. Our model uses three-parameter homographies to connect camera motion to image motion and, by assigning weights to a set of these homographies, can be seen as a generalization of the standard, spatially-invariant convolutional model of image blur. As such we show how existing algorithms, designed for spatially-invariant deblurring, can be "upgraded" in a straightforward manner to handle spatially-variant blur instead. We demonstrate this with algorithms working on real images, showing results for blind estimation of blur parameters from single images, followed by non-blind image restoration using these parameters. Finally, we introduce an efficient approximation to the global model, which significantly reduces the computational cost of modeling the spatially-variant blur. By approximating the blur as locally-uniform, we can take advantage of fast Fourier-domain convolution and deconvolution, reducing the time required for blind deblurring by an order of magnitude.

https://hal.inria.fr/hal-01063814/document

Efficient, Blind, Spatially-Variant Deblurring for Shaken Images

Discussion for direct versus features session

In this work, we introduce the BBC-Oxford British Sign Language (BOBSL)
dataset, a large-scale video collection of British Sign Language (BSL). BOBSL
is an extended and publicly released dataset based on the BSL-1K dataset
introduced in previous work. We describe the motivation for the dataset,
together with statistics and available annotations. We conduct experiments to
provide baselines for the tasks of sign recognition, sign language alignment,
and sign language translation. Finally, we describe several strengths and
limitations of the data from the perspectives of machine learning and
linguistics, note sources of bias present in the dataset, and discuss potential
applications of BOBSL in the context of sign language technology. The dataset
is available at https://www.robots.ox.ac.uk/~vgg/data/bobsl/.

BBC-Oxford British Sign Language Dataset.

In this paper, we consider the task of spotting spoken keywords in silent video sequences -- also known as visual keyword spotting. To this end, we investigate Transformer-based models that ingest two streams, a visual encoding of the video and a phonetic encoding of the keyword, and output the temporal location of the keyword if present. Our contributions are as follows: (1) We propose a novel architecture, the Transpotter, that uses full cross-modal attention between the visual and phonetic streams; (2) We show through extensive evaluations that our model outperforms the prior state-of-the-art visual keyword spotting and lip reading methods on the challenging LRW, LRS2, LRS3 datasets by a large margin; (3) We demonstrate the ability of our model to spot words under the extreme conditions of isolated mouthings in sign language videos.

Visual keyword spotting with attention

Archival research is haunted by the question of how complete are the archival fonds being consulted. In this article, we describe how we have used a combination of pattern-matching and face-recogni...

Andrew Zisserman

Papers

Efficient, Blind, Spatially-Variant Deblurring for Shaken Images

Discussion for direct versus features session

BBC-Oxford British Sign Language Dataset.

Visual keyword spotting with attention

Bounding an archiving: assessing the relative completeness of the Jacques Toussele archive using pattern-matching and face-recognition