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

It is known that rotationally symmetric surfaces can be recognized from their outlines alone, using cross-ratios of bitangent intersections. A successful implementation of this technique is demonstrated using a novel bitangent finder which works on images of real scenes. The stability of the cross-ratios is reported and compared to affine invariants. The recognition technique is shown to extend to the case of straight homogeneous generalized cylinders. >

Efficient recognition of rotationally symmetric surfaces and straight homogeneous generalized cylinders

We demonstrate the recovery of 3D structure from multiple images, without attempting to determine the motion between views. The structure is recovered up to a transformation by a 3D linear group — the affine and projective group. The recovery does not require knowledge of camera intrinsic parameters or camera motion.

/pdf/affine-and-projective-structure-from-motion-3ikxjinz8n.pdf

Affine and Projective Structure from Motion

We describe a novel approach to reconstructing the complete surface of an object from multiple views, where the camera circumnavigates the object. The approach combines the information available from the apparent contour with the information available from the imaged surface texture.

Surface reconstruction from multiple views using apparent contours and surface texture

Histograms of visual words (or textons) have proved effective in tasks such as image classification and object class recognition. A common approach is to represent an object class by a set of histograms, each one corresponding to a training exemplar. Classification is then achieved by k-nearest neighbour search over the exemplars.

In this paper we introduce two novelties on this approach: (i) we show that new compact single histogram models estimated optimally from the entire training set achieve an equal or superior classification accuracy. The benefit of the single histograms is that they are much more efficient both in terms of memory and computational resources; and (ii) we show that bag of visual words histograms can provide an accurate pixel-wise segmentation of an image into object class regions. In this manner the compact models of visual object classes give simultaneous segmentation and recognition of image regions.

The approach is evaluated on the MSRC database [5] and it is shown that performance equals or is superior to previous publications on this database.

/pdf/single-histogram-class-models-for-image-segmentation-1cxmsnaucm.pdf

Single-Histogram class models for image segmentation

We propose a two-stream convolutional network for audio recognition, that operates on time-frequency spectrogram inputs. Following similar success in visual recognition, we learn Slow-Fast auditory streams with separable convolutions and multi-level lateral connections. The Slow pathway has high channel capacity while the Fast pathway operates at a fine-grained temporal resolution. We showcase the importance of our two-stream proposal on two diverse datasets: VGG-Sound and EPIC-KITCHENS-100, and achieve state- of-the-art results on both.

Andrew Zisserman

Papers

Efficient recognition of rotationally symmetric surfaces and straight homogeneous generalized cylinders

Affine and Projective Structure from Motion

Surface reconstruction from multiple views using apparent contours and surface texture

Single-Histogram class models for image segmentation

Slow-Fast Auditory Streams for Audio Recognition