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.

Effective robotic interaction with household objects requires the ability to recognize both object instances and object categories. The former are often characterized by locally discriminative texture cues (e.g., instances with prominent brand names and logos), and the latter by salient global shape properties (plates, bowls, pots). We describe experiments with both types of cues, combining a template-and-deformable-parts detector to capture overall shape properties with a local feature Naive-Bayes nearest neighbor model to capture local texture properties. We base our implementation on the recently introduced Kinect sensor, which provides reliable depth estimates of indoor scenes. Depth cues provide segmentation and size constraints to our method. Depth affinity is used to modify the appearance term in a segmentation-based proposal step, and size priors are imposed on object classes to prune false positives. We address the complexity of scanning window HOG search using multi-class pruning schemes, first applying a generic object detection scheme to prune unlikely windows, and then focusing only on the most likely class per remaining window. Our method is able to handle relatively cluttered scenes involving multiple objects with varying levels of surface texture, and can efficiently employ multi-class scanning window search.

/pdf/practical-3-d-object-detection-using-category-and-instance-at2khgwhjh.pdf

Practical 3-D Object detection using category and instance-level appearance models

Multi-modal data collections, such as corpora of paired images and text snippets, require analysis methods beyond single-view component and topic models. For continuous observations the current dominant approach is based on extensions of canonical correlation analysis, factorizing the variation into components shared by the different modalities and those private to each of them. For count data, multiple variants of topic models attempting to tie the modalities together have been presented. All of these, however, lack the ability to learn components private to one modality, and consequently will try to force dependencies even between minimally correlating modalities. In this work we combine the two approaches by presenting a novel HDP-based topic model that automatically learns both shared and private topics. The model is shown to be especially useful for querying the contents of one domain given samples of the other.

Factorized Multi-Modal Topic Model

Multiple instance learning (MIL) is a branch of machine learning that attempts to learn information from bags of instances. Many real-world applications such as localized content-based image retrieval and text categorization can be viewed as MIL problems. In this paper, we propose a new graph-based semi-supervised learning approach for multiple instance learning. By defining an instance-level graph on the data, we first propose a new approach to construct an optimization framework for multiple instance semi-supervised learning, and derive an efficient way to overcome the non-convexity of MIL. We empirically show that our method outperforms state-of-the-art MIL algorithms on several real-world data sets.

/pdf/instance-level-semisupervised-multiple-instance-learning-abxifsc45f.pdf

Instance-level semisupervised multiple instance learning

Systems and techniques are provided for a ranking approach to train deep neural nets for multilabel image annotation. Label scores may be received for labels determined by a neural network for training examples. Each label may be a positive label or a negative label for the training example. An error of the neural network may be determined based on a comparison, for each of the training examples, of the label scores for positive labels and negative labels for the training example and a semantic distance between each positive label and each negative label for the training example. Updated weights may be determined for the neural network based on a gradient of the determined error of the neural network. The updated weights may be applied to the neural network to train the neural network.

Ranking approach to train deep neural nets for multilabel image annotation

In this paper, we propose regularized tree partitioning approaches. We study normalized cut (NCut) and average cut (ACut) criteria over a tree, forming two approaches: 1) normalized tree partitioning (NTP) and 2) average tree partitioning (ATP). We give the properties that result in an efficient algorithm for NTP and ATP. In addition, we present the relations between the solutions of NTP and ATP over the maximum weight spanning tree of a graph and NCut and ACut over this graph. To demonstrate the effectiveness of the proposed approaches, we show its application to image segmentation over the Berkeley image segmentation data set and present qualitative and quantitative comparisons with state-of-the-art methods.

/pdf/regularized-tree-partitioning-and-its-application-to-5cinatdbdf.pdf

Yangqing Jia

Papers

Practical 3-D Object detection using category and instance-level appearance models

Factorized Multi-Modal Topic Model

Instance-level semisupervised multiple instance learning

Ranking approach to train deep neural nets for multilabel image annotation

Regularized Tree Partitioning and Its Application to Unsupervised Image Segmentation