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

A requirement of a visual measurement device is that both measurements and their uncertainties can be determined. This paper develops an uncertainty analysis which includes both the errors in image localization and the uncertainty in the imaging transformation. The matrix representing the imaging transformation is estimated from image-to-world point correspondences. A general expression is derived for the covariance of this matrix. This expression is valid if the matrix is over determined and also if the minimum number of correspondences are used. A bound on the errors of the first order approximations involved is also derived. Armed with this covariance result the uncertainty of any measurement can be predicted, and furthermore the distribution of correspondences can be chosen to achieve a particular bound on the uncertainty. Examples are given of measurements such as distance and parallelism for several applications. These include indoor scenes and architectural measurements.

A Plane Measuring Device.

Human pose as a query modality is an alternative and rich experience for image and video retrieval. We present a novel approach for the task of human pose retrieval, and make the following contributions: first, we introduce ‘deep poselets’ for pose-sensitive detection of various body parts, that are built on convolutional neural network (CNN) features. These deep poselets significantly outperform previous instantiations of Berkeley poselets [2]. Second, using these detector responses, we construct a pose representation that is suitable for pose search, and show that pose retrieval performance exceeds previous methods by a factor of two. The compared methods include Bag of visual words [24], Berkeley poselets [2] and Human pose estimation algorithms [28]. All the methods are quantitatively evaluated on a large dataset of images built from a number of standard benchmarks together with frames from Hollywood movies.

/pdf/human-pose-search-using-deep-poselets-3jvb74agpt.pdf

Human pose search using deep poselets

Human pose search using deep networks

We introduce QuerYD, a new large-scale dataset for retrieval and event localisation in video. A unique feature of our dataset is the availability of two audio tracks for each video: the original audio, and a high-quality spoken description of the visual content. The dataset is based on YouDescribe [1], a volunteer project that assists visually-impaired people by attaching voiced narrations to existing YouTube videos. This ever-growing collection of videos contains highly detailed, temporally aligned audio and text annotations. The content descriptions are more relevant than dialogue, and more detailed than previous description attempts, which can be observed to contain many superficial or uninformative descriptions. To demonstrate the utility of the QuerYD dataset, we show that it can be used to train and benchmark strong models for retrieval and event localisation. Data, code and models are made publicly available, and we hope that QuerYD inspires further research on video understanding with written and spoken natural language.

QUERYD: A Video Dataset with High-Quality Text and Audio Narrations

The recently-proposed Perceiver model obtains good results on several domains
(images, audio, multimodal, point clouds) while scaling linearly in compute and
memory with the input size. While the Perceiver supports many kinds of inputs,
it can only produce very simple outputs such as class scores. Perceiver IO
overcomes this limitation without sacrificing the original's appealing
properties by learning to flexibly query the model's latent space to produce
outputs of arbitrary size and semantics. Perceiver IO still decouples model
depth from data size and still scales linearly with data size, but now with
respect to both input and output sizes. The full Perceiver IO model achieves
strong results on tasks with highly structured output spaces, such as natural
language and visual understanding, StarCraft II, and multi-task and multi-modal
domains. As highlights, Perceiver IO matches a Transformer-based BERT baseline
on the GLUE language benchmark without the need for input tokenization and
achieves state-of-the-art performance on Sintel optical flow estimation.

/pdf/perceiver-io-a-general-architecture-for-structured-inputs-e82lsbay8l.pdf

Andrew Zisserman

Papers

A Plane Measuring Device.

Human pose search using deep poselets

Human pose search using deep networks

QUERYD: A Video Dataset with High-Quality Text and Audio Narrations

Perceiver IO: A General Architecture for Structured Inputs & Outputs