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

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

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---8x deeper than VGG nets 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 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

Embodiments related to the removal of blur from an image are disclosed. One disclosed embodiment provides a method of performing an iterative non-blind deconvolution of a blurred image to form an updated image. The method comprises downsampling the blurred image to form a blurred image pyramid comprising images of two or more different resolution scales, downsampling a blur kernel to form a blur kernel pyramid comprising kernels of two or more different sizes, and deconvoluting a selected image in the blurred image pyramid according to a Richardson-Lucy deconvolution process in which a bilateral range/spatial filter is employed.

Removing blur from an image

Techniques and systems for providing textual attribute-based image categorization and search are disclosed herein In some aspects, images may be analyzed to identify a category of an image, or portion thereof Additional textual attributes may be identified and associated with the image In various aspects, the categories may be types of sky sceneries Categorized images may be searched based on the categories and/or attributes In further aspects, a user interface may provide an intuitive arrangement of the images for user navigation and selection The user interface may also provide a simplified presentation and search of the categorized images Images selected from user interface may be used to replace or modify features of an existing target image

Textual attribute-based image categorization and search

Sparse coding is a widely involved technique in computer vision. However, the expensive computational cost can hamper its applications, typically when the codebook size must be limited due to concerns on running time. In this paper, we study a special case of sparse coding in which the codebook is a Cartesian product of two subcodebooks. We present algorithms to decompose this sparse coding problem into smaller subproblems, which can be separately solved. Our solution, named as Product Sparse Coding (PSC), reduces the time complexity from O(K) to O(rK) in the codebook size K. In practice, this can be 20-100x faster than standard sparse coding. In experiments we demonstrate the efficiency and quality of this method on the applications of image classification and image retrieval.

/pdf/product-sparse-coding-1scq1efiqn.pdf

Product Sparse Coding

The manipulation of panoramic/wide-angle images is usually achieved via image warping. Though various techniques have been developed for preserving shapes and straight lines for warping, these are not sufficient for panoramic/wide-angle images. The image projections will turn the straight lines into curved “geodesic lines”, and it is fundamentally impossible to keep all these lines straight. In this work, we propose a geodesic-preserving method for content-aware image warping. An energy term is introduced to preserve the geodesic appearance of the geodesic lines, and can be used with shape-preserving terms. Our method is demonstrated in various applications, including rectangling panoramas, resizing panoramic/wide-angle images, and wide-angle image manipulation. An extension to ellipse preservation for general images is also presented.

/pdf/a-geodesic-preserving-method-for-image-warping-337gl1rlxb.pdf

A geodesic-preserving method for image warping

A geodesic is a parameterized curve on a Riemannian manifold governed by a second order partial differential equation. Geodesics are notoriously unstable: small perturbations of the underlying manifold may lead to dramatic changes of the course of a geodesic. Such instability makes it difficult to use geodesics in many applications, in particular in the world of discrete geometry. In this paper, we consider a geodesic as the indicator function of the set of the points on the geodesic. From this perspective, we present a new concept called fuzzy geodesics and show that fuzzy geodesics are stable with respect to the Gromov-Hausdorff distance. Based on fuzzy geodesics, we propose a new object called the intersection configuration for a set of points on a shape and demonstrate its effectiveness in the application of finding consistent correspondences between sparse sets of points on shapes differing by extreme deformations.

Jian Sun

Papers

Removing blur from an image

Textual attribute-based image categorization and search

Product Sparse Coding

A geodesic-preserving method for image warping

Fuzzy Geodesics and Consistent Sparse Correspondences For: eformable Shapes