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

We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

/pdf/going-deeper-with-convolutions-1yobw2o2ds.pdf

Going deeper with convolutions

Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones; a graph of these hierarchies would be many layers deep. This book introduces a broad range of topics in deep learning. The text offers mathematical and conceptual background, covering relevant concepts in linear algebra, probability theory and information theory, numerical computation, and machine learning. It describes deep learning techniques used by practitioners in industry, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology; and it surveys such applications as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames. Finally, the book offers research perspectives, covering such theoretical topics as linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods, the partition function, approximate inference, and deep generative models. Deep Learning can be used by undergraduate or graduate students planning careers in either industry or research, and by software engineers who want to begin using deep learning in their products or platforms. A website offers supplementary material for both readers and instructors.

Deep Learning

There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.

Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

I and i

We present a new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene understanding. This is achieved by gathering images of complex everyday scenes containing common objects in their natural context. Objects are labeled using per-instance segmentations to aid in precise object localization. Our dataset contains photos of 91 objects types that would be easily recognizable by a 4 year old. With a total of 2.5 million labeled instances in 328k images, the creation of our dataset drew upon extensive crowd worker involvement via novel user interfaces for category detection, instance spotting and instance segmentation. We present a detailed statistical analysis of the dataset in comparison to PASCAL, ImageNet, and SUN. Finally, we provide baseline performance analysis for bounding box and segmentation detection results using a Deformable Parts Model.

/pdf/microsoft-coco-common-objects-in-context-55ihxq1zt5.pdf

Microsoft COCO: Common Objects in Context

Tracking the 3-D pose of an object needs correspondences between 2-D features in the image and their 3-D counterparts in the object model. A large variety of such features has been suggested in the literature. All of them have drawbacks in one situation or the other since their extraction in the image and/or the matching is prone to errors. In this paper, we propose to use two complementary types of features for pose tracking, such that one type makes up for the shortcomings of the other. Aside from the object contour, which is matched to a free-form object surface, we suggest to employ the optic flow in order to compute additional point correspondences. Optic flow estimation is a mature research field with sophisticated algorithms available. Using here a high quality method ensures a reliable matching. In our experiments we demonstrate the performance of our method and in particular the improvements due to the optic flow.

High Accuracy Optical Flow Serves 3-D Pose Tracking : Exploiting Contour and Flow Based Constraints

Convolutional networks reach top quality in pixel-level video object segmentation but require a large amount of training data (1k~100k) to deliver such results. We propose a new training strategy which achieves state-of-the-art results across three evaluation datasets while using 20x~1000x less annotated data than competing methods. Our approach is suitable for both single and multiple object segmentation. Instead of using large training sets hoping to generalize across domains, we generate in-domain training data using the provided annotation on the first frame of each video to synthesize ("lucid dream") plausible future video frames. In-domain per-video training data allows us to train high quality appearance- and motion-based models, as well as tune the post-processing stage. This approach allows to reach competitive results even when training from only a single annotated frame, without ImageNet pre-training. Our results indicate that using a larger training set is not automatically better, and that for the video object segmentation task a smaller training set that is closer to the target domain is more effective. This changes the mindset regarding how many training samples and general "objectness" knowledge are required for the video object segmentation task.

Lucid Data Dreaming for Video Object Segmentation

Machine learning methods in general and Deep Neural Networks in particular have shown to be vulnerable to adversarial perturbations. So far this phenomenon has mainly been studied in the context of whole-image classification. In this contribution, we analyse how adversarial perturbations can affect the task of semantic segmentation. We show how existing adversarial attackers can be transferred to this task and that it is possible to create imperceptible adversarial perturbations that lead a deep network to misclassify almost all pixels of a chosen class while leaving network prediction nearly unchanged outside this class.

Adversarial Examples for Semantic Image Segmentation

Natural image statistics indicate that we should use non-convex norms for most regularization tasks in image processing and computer vision. Still, they are rarely used in practice due to the challenge to optimize them. Recently, iteratively reweighed l1 minimization has been proposed as a way to tackle a class of non-convex functions by solving a sequence of convex l2 - l1 problems. Here we extend the problem class to linearly constrained optimization of a Lipschitz continuous function, which is the sum of a convex function and a function being concave and increasing on the non-negative orthant (possibly non-convex and non-concave on the whole space). This allows to apply the algorithm to many computer vision tasks. We show the effect of non-convex regularizers on image denoising, deconvolution, optical flow, and depth map fusion. Non-convexity is particularly interesting in combination with total generalized variation and learned image priors. Efficient optimization is made possible by some important properties that are shown to hold.

/pdf/an-iterated-l1-algorithm-for-non-smooth-non-convex-464ijmt785.pdf

An Iterated L1 Algorithm for Non-smooth Non-convex Optimization in Computer Vision

This work deals with modeling and markerless tracking of athletes interacting with sports gear. In contrast to classical markerless tracking, the interaction with sports gear comes along with joint movement restrictions due to additional constraints: while humans can generally use all their joints, interaction with the equipment imposes a coupling between certain joints. A cyclist who performs a cycling pattern is one example: The feet are supposed to stay on the pedals, which are again restricted to move along a circular trajectory in 3D-space. In this paper, we present a markerless motion capture system that takes the lower-dimensional pose manifold into account by modeling the motion restrictions via soft constraints during pose optimization. Experiments with two different models, a cyclist and a snowboarder, demonstrate the applicability of the method. Moreover, we present motion capture results for challenging outdoor scenes including shadows and strong illumination changes.

/pdf/markerless-motion-capture-of-man-machine-interaction-3v2vb0crec.pdf

Thomas Brox

Papers

High Accuracy Optical Flow Serves 3-D Pose Tracking : Exploiting Contour and Flow Based Constraints

Lucid Data Dreaming for Video Object Segmentation

Adversarial Examples for Semantic Image Segmentation

An Iterated L1 Algorithm for Non-smooth Non-convex Optimization in Computer Vision

Markerless motion capture of man-machine interaction