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

This work presents a method for visual text recognition without using any paired supervisory data. We formulate the text recognition task as one of aligning the conditional distribution of strings predicted from given text images, with lexically valid strings sampled from target corpora. This enables fully automated, and unsupervised learning from just line-level text-images, and unpaired text-string samples, obviating the need for large aligned datasets. We present detailed analysis for various aspects of the proposed method, namely --- (1) impact of the length of training sequences on convergence, (2) relation between character frequencies and the order in which they are learnt, (3) generalisation ability of our recognition network to inputs of arbitrary lengths, and (4) impact of varying the text corpus on recognition accuracy. Finally, we demonstrate excellent text recognition accuracy on both synthetically generated text images, and scanned images of real printed books, using no labelled training examples.

Learning to Read by Spelling: Towards Unsupervised Text Recognition

We describe progress on automating the construction of 3D geometric models from video sequences. The system we are developing allows a person to walk around a room with a video camera, and from the video sequence alone extract a 3D model of the room. The room can then be graphically rendered together with possible arrangements of previously modelled objects, e.g. CAD models of furniture. The system is designed to ease model acquisition for virtual reality and telepresence applications, however the approach also has application in model based image coding. The approach is based on recent work in computer vision where image primitives are extracted and matched through an image sequence. For example, the simultaneous estimation of epipolar geometry and image corner correspondences. The matching techniques are both robust (detecting and discarding mismatches) and fully automatic. No knowledge of the camera (e.g. its focal length) or motion is required. 3D structure is computed from the matched image primitives (corners, lines and texture). The structure is then triangulated and texture is mapped onto the triangles from intensities in the images. Experimental results are provided for a variety of scenes, including isolated objects acquired with a standard CCD camera, and outdoor scenes acquired with a hand-held camcorder.

Automatic 3D model building from video sequences

Grouping and invariants using planar homologies

An approach to path-planning around smooth obstacles that exploits visually derived geometry is proposed. A moving robot can scan the silhouette or apparent contour of an obstacle and estimate a minimum length path. This is done by seeking geodesics which can be extrapolated smoothly, around the obstacle and towards the goal. Preliminary implementation of this idea uses a real-time visual contour tracker running at 16 Hz, with a camera mounted on an Adept robot arm. The camera first dithers to generate visual motion, a safe path is estimated, and the robot steers the camera around the obstacle with a clearance of a few millimeters. >

Visual navigation around curved obstacles

We present a parts and structure model for object category recognition that can be learnt efficiently and in a weakly-supervised manner: the model is learnt from example images containing category instances, without requiring segmentation from background clutter. The model is a sparse representation of the object, and consists of a star topology configuration of parts modeling the output of a variety of feature detectors. The optimal choice of feature types (whose repertoire includes interest points, curves and regions) is made automatically. In recognition, the model may be applied efficiently in a complete manner, bypassing the need for feature detectors, to give the globally optimal match within a query image. The approach is demonstrated on a wide variety of categories, and delivers both successful classification and localization of the object within the image.

Andrew Zisserman

Papers

Learning to Read by Spelling: Towards Unsupervised Text Recognition

Automatic 3D model building from video sequences

Grouping and invariants using planar homologies

Visual navigation around curved obstacles

A sparse object category model for efficient learning and complete recognition