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.

This paper addresses the problem of learning long binary codes from high-dimensional data. We observe that two key challenges arise while learning and using long binary codes: (1) lack of an effective regularizer for the learned high-dimensional mapping and (2) high computational cost for computing long codes. In this paper, we overcome both these problems by introducing a sparsity encouraging regularizer that reduces the effective number of parameters involved in the learned projection operator. This regularizer not only reduces overfitting but, due to the sparse nature of the projection matrix, also leads to a dramatic reduction in the computational cost. To evaluate the effectiveness of our method, we analyze its performance on the problems of nearest neighbour search, image retrieval and image classification. Experiments on a number of challenging datasets show that our method leads to better accuracy than dense projections (ITQ [11] and LSH [16]) with the same code lengths, and meanwhile is over an order of magnitude faster. Furthermore, our method is also more accurate and faster than other recently proposed methods for speeding up high-dimensional binary encoding.

/pdf/sparse-projections-for-high-dimensional-binary-codes-14wzrem6t2.pdf

Sparse projections for high-dimensional binary codes

We present region-based, fully convolutional networks for accurate and efficient object detection. In contrast to previous region-based detectors such as Fast/Faster R-CNN that apply a costly per-region subnetwork hundreds of times, our region-based detector is fully convolutional with almost all computation shared on the entire image. To achieve this goal, we propose position-sensitive score maps to address a dilemma between translation-invariance in image classification and translation-variance in object detection. Our method can thus naturally adopt fully convolutional image classifier backbones, such as the latest Residual Networks (ResNets), for object detection. We show competitive results on the PASCAL VOC datasets (e.g., 83.6% mAP on the 2007 set) with the 101-layer ResNet. Meanwhile, our result is achieved at a test-time speed of 170ms per image, 2.5-20x faster than the Faster R-CNN counterpart. Code is made publicly available at: this https URL

R-FCN: Object Detection via Region-based Fully Convolutional Networks

Learning short binary codes is challenged by the inherent discrete nature of the problem. The graph cuts algorithm is a well-studied discrete label assignment solution in computer vision, but has not yet been applied to solve the binary coding problems. This is partially because it was unclear how to use it to learn the encoding (hashing) functions for out-of-sample generalization. In this paper, we formulate supervised binary coding as a single optimization problem that involves both the encoding functions and the binary label assignment. Then we apply the graph cuts algorithm to address the discrete optimization problem involved, with no continuous relaxation. This method, named as Graph Cuts Coding (GCC), shows competitive results in various datasets.

/pdf/graph-cuts-for-supervised-binary-coding-4r14hyqyud.pdf

Graph Cuts for Supervised Binary Coding

Stitched panoramic images mostly have irregular boundaries. Artists and common users generally prefer rectangular boundaries, which can be obtained through cropping or image completion techniques. In this paper, we present a content-aware warping algorithm that generates rectangular images from stitched panoramic images. Our algorithm consists of two steps. The first local step is mesh-free and preliminarily warps the image into a rectangle. With a grid mesh placed on this rectangle, the second global step optimizes the mesh to preserve shapes and straight lines. In various experiments we demonstrate that the results of our approach are often visually plausible, and the introduced distortion is often unnoticeable.

Rectangling panoramic images via warping

Inverted indexing is a popular non-exhaustive solution to large scale search. An inverted file is built by a quantizer such as k-means or a tree structure. It has been found that multiple inverted files, obtained by multiple independent random quantizers, are able to achieve practically good recall and speed. Instead of computing the multiple quantizers independently, we present a method that creates them jointly. Our method jointly optimizes all code words in all quantizers. Then it assigns these code words to the quantizers. In experiments this method shows significant improvement over various existing methods that use multiple independent quantizers. On the one-billion set of SIFT vectors, our method is faster and more accurate than a recent state-of-the-art inverted indexing method.

/pdf/joint-inverted-indexing-3s0rma6rt6.pdf

Kaiming He

Papers

Sparse projections for high-dimensional binary codes

R-FCN: Object Detection via Region-based Fully Convolutional Networks

Graph Cuts for Supervised Binary Coding

Rectangling panoramic images via warping

Joint Inverted Indexing