October 19, 2019

3436 words 17 mins read

Paper Group ANR 262

Solving stochastic differential equations and Kolmogorov equations by means of deep learning. A Novel Domain Adaptation Framework for Medical Image Segmentation. Cubes3D: Neural Network based Optical Flow in Omnidirectional Image Scenes. AIRNet: Self-Supervised Affine Registration for 3D Medical Images using Neural Networks. Weakly-Supervised Learn …

Solving stochastic differential equations and Kolmogorov equations by means of deep learning


Title	Solving stochastic differential equations and Kolmogorov equations by means of deep learning
Authors	Christian Beck, Sebastian Becker, Philipp Grohs, Nor Jaafari, Arnulf Jentzen
Abstract	Stochastic differential equations (SDEs) and the Kolmogorov partial differential equations (PDEs) associated to them have been widely used in models from engineering, finance, and the natural sciences. In particular, SDEs and Kolmogorov PDEs, respectively, are highly employed in models for the approximative pricing of financial derivatives. Kolmogorov PDEs and SDEs, respectively, can typically not be solved explicitly and it has been and still is an active topic of research to design and analyze numerical methods which are able to approximately solve Kolmogorov PDEs and SDEs, respectively. Nearly all approximation methods for Kolmogorov PDEs in the literature suffer under the curse of dimensionality or only provide approximations of the solution of the PDE at a single fixed space-time point. In this paper we derive and propose a numerical approximation method which aims to overcome both of the above mentioned drawbacks and intends to deliver a numerical approximation of the Kolmogorov PDE on an entire region $[a,b]^d$ without suffering from the curse of dimensionality. Numerical results on examples including the heat equation, the Black-Scholes model, the stochastic Lorenz equation, and the Heston model suggest that the proposed approximation algorithm is quite effective in high dimensions in terms of both accuracy and speed.
Tasks
Published	2018-06-01
URL	http://arxiv.org/abs/1806.00421v1
PDF	http://arxiv.org/pdf/1806.00421v1.pdf
PWC	https://paperswithcode.com/paper/solving-stochastic-differential-equations-and
Repo
Framework

A Novel Domain Adaptation Framework for Medical Image Segmentation


Title	A Novel Domain Adaptation Framework for Medical Image Segmentation
Authors	Amir Gholami, Shashank Subramanian, Varun Shenoy, Naveen Himthani, Xiangyu Yue, Sicheng Zhao, Peter Jin, George Biros, Kurt Keutzer
Abstract	We propose a segmentation framework that uses deep neural networks and introduce two innovations. First, we describe a biophysics-based domain adaptation method. Second, we propose an automatic method to segment white and gray matter, and cerebrospinal fluid, in addition to tumorous tissue. Regarding our first innovation, we use a domain adaptation framework that combines a novel multispecies biophysical tumor growth model with a generative adversarial model to create realistic looking synthetic multimodal MR images with known segmentation. Regarding our second innovation, we propose an automatic approach to enrich available segmentation data by computing the segmentation for healthy tissues. This segmentation, which is done using diffeomorphic image registration between the BraTS training data and a set of prelabeled atlases, provides more information for training and reduces the class imbalance problem. Our overall approach is not specific to any particular neural network and can be used in conjunction with existing solutions. We demonstrate the performance improvement using a 2D U-Net for the BraTS’18 segmentation challenge. Our biophysics based domain adaptation achieves better results, as compared to the existing state-of-the-art GAN model used to create synthetic data for training.
Tasks	Domain Adaptation, Image Registration, Medical Image Segmentation, Semantic Segmentation
Published	2018-10-11
URL	http://arxiv.org/abs/1810.05732v1
PDF	http://arxiv.org/pdf/1810.05732v1.pdf
PWC	https://paperswithcode.com/paper/a-novel-domain-adaptation-framework-for
Repo
Framework

Cubes3D: Neural Network based Optical Flow in Omnidirectional Image Scenes


Title	Cubes3D: Neural Network based Optical Flow in Omnidirectional Image Scenes
Authors	André Apitzsch, Roman Seidel, Gangolf Hirtz
Abstract	Optical flow estimation with convolutional neural networks (CNNs) has recently solved various tasks of computer vision successfully. In this paper we adapt a state-of-the-art approach for optical flow estimation to omnidirectional images. We investigate CNN architectures to determine high motion variations caused by the geometry of fish-eye images. Further we determine the qualitative influence of texture on the non-rigid object to the motion vectors. For evaluation of the results we create ground truth motion fields synthetically. The ground truth contains cubes with static background. We test variations of pre-trained FlowNet 2.0 architectures by indicating common error metrics. We generate competitive results for the motion of the foreground with inhomogeneous texture on the moving object.
Tasks	Optical Flow Estimation
Published	2018-04-24
URL	http://arxiv.org/abs/1804.09004v2
PDF	http://arxiv.org/pdf/1804.09004v2.pdf
PWC	https://paperswithcode.com/paper/cubes3d-neural-network-based-optical-flow-in
Repo
Framework

AIRNet: Self-Supervised Affine Registration for 3D Medical Images using Neural Networks


Title	AIRNet: Self-Supervised Affine Registration for 3D Medical Images using Neural Networks
Authors	Evelyn Chee, Zhenzhou Wu
Abstract	In this work, we propose a self-supervised learning method for affine image registration on 3D medical images. Unlike optimisation-based methods, our affine image registration network (AIRNet) is designed to directly estimate the transformation parameters between two input images without using any metric, which represents the quality of the registration, as the optimising function. But since it is costly to manually identify the transformation parameters between any two images, we leverage the abundance of cheap unlabelled data to generate a synthetic dataset for the training of the model. Additionally, the structure of AIRNet enables us to learn the discriminative features of the images which are useful for registration purpose. Our proposed method was evaluated on magnetic resonance images of the axial view of human brain and compared with the performance of a conventional image registration method. Experiments demonstrate that our approach achieves better overall performance on registration of images from different patients and modalities with 100x speed-up in execution time.
Tasks	Image Registration
Published	2018-10-05
URL	http://arxiv.org/abs/1810.02583v2
PDF	http://arxiv.org/pdf/1810.02583v2.pdf
PWC	https://paperswithcode.com/paper/airnet-self-supervised-affine-registration
Repo
Framework

Weakly-Supervised Learning of Metric Aggregations for Deformable Image Registration


Title	Weakly-Supervised Learning of Metric Aggregations for Deformable Image Registration
Authors	Enzo Ferrante, Puneet K. Dokania, Rafael Marini Silva, Nikos Paragios
Abstract	Deformable registration has been one of the pillars of biomedical image computing. Conventional approaches refer to the definition of a similarity criterion that, once endowed with a deformation model and a smoothness constraint, determines the optimal transformation to align two given images. The definition of this metric function is among the most critical aspects of the registration process. We argue that incorporating semantic information (in the form of anatomical segmentation maps) into the registration process will further improve the accuracy of the results. In this paper, we propose a novel weakly supervised approach to learn domain specific aggregations of conventional metrics using anatomical segmentations. This combination is learned using latent structured support vector machines (LSSVM). The learned matching criterion is integrated within a metric free optimization framework based on graphical models, resulting in a multi-metric algorithm endowed with a spatially varying similarity metric function conditioned on the anatomical structures. We provide extensive evaluation on three different datasets of CT and MRI images, showing that learned multi-metric registration outperforms single-metric approaches based on conventional similarity measures.
Tasks	Image Registration
Published	2018-09-24
URL	http://arxiv.org/abs/1809.09004v1
PDF	http://arxiv.org/pdf/1809.09004v1.pdf
PWC	https://paperswithcode.com/paper/weakly-supervised-learning-of-metric
Repo
Framework

Multi-view Consistency as Supervisory Signal for Learning Shape and Pose Prediction


Title	Multi-view Consistency as Supervisory Signal for Learning Shape and Pose Prediction
Authors	Shubham Tulsiani, Alexei A. Efros, Jitendra Malik
Abstract	We present a framework for learning single-view shape and pose prediction without using direct supervision for either. Our approach allows leveraging multi-view observations from unknown poses as supervisory signal during training. Our proposed training setup enforces geometric consistency between the independently predicted shape and pose from two views of the same instance. We consequently learn to predict shape in an emergent canonical (view-agnostic) frame along with a corresponding pose predictor. We show empirical and qualitative results using the ShapeNet dataset and observe encouragingly competitive performance to previous techniques which rely on stronger forms of supervision. We also demonstrate the applicability of our framework in a realistic setting which is beyond the scope of existing techniques: using a training dataset comprised of online product images where the underlying shape and pose are unknown.
Tasks	Pose Prediction
Published	2018-01-11
URL	http://arxiv.org/abs/1801.03910v2
PDF	http://arxiv.org/pdf/1801.03910v2.pdf
PWC	https://paperswithcode.com/paper/multi-view-consistency-as-supervisory-signal
Repo
Framework

Inverse-Consistent Deep Networks for Unsupervised Deformable Image Registration


Title	Inverse-Consistent Deep Networks for Unsupervised Deformable Image Registration
Authors	Jun Zhang
Abstract	Deformable image registration is a fundamental task in medical image analysis, aiming to establish a dense and non-linear correspondence between a pair of images. Previous deep-learning studies usually employ supervised neural networks to directly learn the spatial transformation from one image to another, requiring task-specific ground-truth registration for model training. Due to the difficulty in collecting precise ground-truth registration, implementation of these supervised methods is practically challenging. Although several unsupervised networks have been recently developed, these methods usually ignore the inherent inverse-consistent property (essential for diffeomorphic mapping) of transformations between a pair of images. Also, existing approaches usually encourage the to-be-estimated transformation to be locally smooth via a smoothness constraint only, which could not completely avoid folding in the resulting transformation. To this end, we propose an Inverse-Consistent deep Network (ICNet) for unsupervised deformable image registration. Specifically, we develop an inverse-consistent constraint to encourage that a pair of images are symmetrically deformed toward one another, until both warped images are matched. Besides using the conventional smoothness constraint, we also propose an anti-folding constraint to further avoid folding in the transformation. The proposed method does not require any supervision information, while encouraging the diffeomoprhic property of the transformation via the proposed inverse-consistent and anti-folding constraints. We evaluate our method on T1-weighted brain magnetic resonance imaging (MRI) scans for tissue segmentation and anatomical landmark detection, with results demonstrating the superior performance of our ICNet over several state-of-the-art approaches for deformable image registration. Our code will be made publicly available.
Tasks	Image Registration
Published	2018-09-10
URL	http://arxiv.org/abs/1809.03443v1
PDF	http://arxiv.org/pdf/1809.03443v1.pdf
PWC	https://paperswithcode.com/paper/inverse-consistent-deep-networks-for
Repo
Framework

Weakly Supervised Convolutional LSTM Approach for Tool Tracking in Laparoscopic Videos


Title	Weakly Supervised Convolutional LSTM Approach for Tool Tracking in Laparoscopic Videos
Authors	Chinedu Innocent Nwoye, Didier Mutter, Jacques Marescaux, Nicolas Padoy
Abstract	Purpose: Real-time surgical tool tracking is a core component of the future intelligent operating room (OR), because it is highly instrumental to analyze and understand the surgical activities. Current methods for surgical tool tracking in videos need to be trained on data in which the spatial positions of the tools are manually annotated. Generating such training data is difficult and time-consuming. Instead, we propose to use solely binary presence annotations to train a tool tracker for laparoscopic videos. Methods: The proposed approach is composed of a CNN + Convolutional LSTM (ConvLSTM) neural network trained end-to-end, but weakly supervised on tool binary presence labels only. We use the ConvLSTM to model the temporal dependencies in the motion of the surgical tools and leverage its spatio-temporal ability to smooth the class peak activations in the localization heat maps (Lh-maps). Results: We build a baseline tracker on top of the CNN model and demonstrate that our approach based on the ConvLSTM outperforms the baseline in tool presence detection, spatial localization, and motion tracking by over 5.0%, 13.9%, and 12.6%, respectively. Conclusions: In this paper, we demonstrate that binary presence labels are sufficient for training a deep learning tracking model using our proposed method. We also show that the ConvLSTM can leverage the spatio-temporal coherence of consecutive image frames across a surgical video to improve tool presence detection, spatial localization, and motion tracking. keywords: Surgical workflow analysis, tool tracking, weak supervision, spatio-temporal coherence, ConvLSTM, endoscopic videos
Tasks
Published	2018-12-04
URL	http://arxiv.org/abs/1812.01366v2
PDF	http://arxiv.org/pdf/1812.01366v2.pdf
PWC	https://paperswithcode.com/paper/weakly-supervised-convolutional-lstm-approach
Repo
Framework

Spatio-Temporal Action Graph Networks


Title	Spatio-Temporal Action Graph Networks
Authors	Roei Herzig, Elad Levi, Huijuan Xu, Hang Gao, Eli Brosh, Xiaolong Wang, Amir Globerson, Trevor Darrell
Abstract	Events defined by the interaction of objects in a scene are often of critical importance; yet important events may have insufficient labeled examples to train a conventional deep model to generalize to future object appearance. Activity recognition models that represent object interactions explicitly have the potential to learn in a more efficient manner than those that represent scenes with global descriptors. We propose a novel inter-object graph representation for activity recognition based on a disentangled graph embedding with direct observation of edge appearance. We employ a novel factored embedding of the graph structure, disentangling a representation hierarchy formed over spatial dimensions from that found over temporal variation. We demonstrate the effectiveness of our model on the Charades activity recognition benchmark, as well as a new dataset of driving activities focusing on multi-object interactions with near-collision events. Our model offers significantly improved performance compared to baseline approaches without object-graph representations, or with previous graph-based models.
Tasks	Activity Recognition, Autonomous Driving, Graph Embedding
Published	2018-12-04
URL	https://arxiv.org/abs/1812.01233v2
PDF	https://arxiv.org/pdf/1812.01233v2.pdf
PWC	https://paperswithcode.com/paper/classifying-collisions-with-spatio-temporal
Repo
Framework

A Coupled Evolutionary Network for Age Estimation


Title	A Coupled Evolutionary Network for Age Estimation
Authors	Peipei Li, Yibo Hu, Ran He, Zhenan Sun
Abstract	Age estimation of unknown persons is a challenging pattern analysis task due to the lacking of training data and various aging mechanisms for different people. Label distribution learning-based methods usually make distribution assumptions to simplify age estimation. However, age label distributions are often complex and difficult to be modeled in a parameter way. Inspired by the biological evolutionary mechanism, we propose a Coupled Evolutionary Network (CEN) with two concurrent evolutionary processes: evolutionary label distribution learning and evolutionary slack regression. Evolutionary network learns and refines age label distributions in an iteratively learning way. Evolutionary label distribution learning adaptively learns and constantly refines the age label distributions without making strong assumptions on the distribution patterns. To further utilize the ordered and continuous information of age labels, we accordingly propose an evolutionary slack regression to convert the discrete age label regression into the continuous age interval regression. Experimental results on Morph, ChaLearn15 and MegaAge-Asian datasets show the superiority of our method.
Tasks	Age Estimation
Published	2018-09-20
URL	http://arxiv.org/abs/1809.07447v1
PDF	http://arxiv.org/pdf/1809.07447v1.pdf
PWC	https://paperswithcode.com/paper/a-coupled-evolutionary-network-for-age
Repo
Framework

Graph Matching with Anchor Nodes: A Learning Approach


Title	Graph Matching with Anchor Nodes: A Learning Approach
Authors	Nan Hu, Raif M. Rustamov, Leonidas Guibas
Abstract	In this paper, we consider the weighted graph matching problem with partially disclosed correspondences between a number of anchor nodes. Our construction exploits recently introduced node signatures based on graph Laplacians, namely the Laplacian family signature (LFS) on the nodes, and the pairwise heat kernel map on the edges. In this paper, without assuming an explicit form of parametric dependence nor a distance metric between node signatures, we formulate an optimization problem which incorporates the knowledge of anchor nodes. Solving this problem gives us an optimized proximity measure specific to the graphs under consideration. Using this as a first order compatibility term, we then set up an integer quadratic program (IQP) to solve for a near optimal graph matching. Our experiments demonstrate the superior performance of our approach on randomly generated graphs and on two widely-used image sequences, when compared with other existing signature and adjacency matrix based graph matching methods.
Tasks	Graph Matching
Published	2018-04-10
URL	http://arxiv.org/abs/1804.03715v1
PDF	http://arxiv.org/pdf/1804.03715v1.pdf
PWC	https://paperswithcode.com/paper/graph-matching-with-anchor-nodes-a-learning
Repo
Framework

Graph Saliency Maps through Spectral Convolutional Networks: Application to Sex Classification with Brain Connectivity


Title	Graph Saliency Maps through Spectral Convolutional Networks: Application to Sex Classification with Brain Connectivity
Authors	Salim Arslan, Sofia Ira Ktena, Ben Glocker, Daniel Rueckert
Abstract	Graph convolutional networks (GCNs) allow to apply traditional convolution operations in non-Euclidean domains, where data are commonly modelled as irregular graphs. Medical imaging and, in particular, neuroscience studies often rely on such graph representations, with brain connectivity networks being a characteristic example, while ultimately seeking the locus of phenotypic or disease-related differences in the brain. These regions of interest (ROIs) are, then, considered to be closely associated with function and/or behaviour. Driven by this, we explore GCNs for the task of ROI identification and propose a visual attribution method based on class activation mapping. By undertaking a sex classification task as proof of concept, we show that this method can be used to identify salient nodes (brain regions) without prior node labels. Based on experiments conducted on neuroimaging data of more than 5000 participants from UK Biobank, we demonstrate the robustness of the proposed method in highlighting reproducible regions across individuals. We further evaluate the neurobiological relevance of the identified regions based on evidence from large-scale UK Biobank studies.
Tasks
Published	2018-06-05
URL	http://arxiv.org/abs/1806.01764v1
PDF	http://arxiv.org/pdf/1806.01764v1.pdf
PWC	https://paperswithcode.com/paper/graph-saliency-maps-through-spectral
Repo
Framework

Global and Local Consistent Wavelet-domain Age Synthesis


Title	Global and Local Consistent Wavelet-domain Age Synthesis
Authors	Peipei Li, Yibo Hu, Ran He, Zhenan Sun
Abstract	Age synthesis is a challenging task due to the complicated and non-linear transformation in human aging process. Aging information is usually reflected in local facial parts, such as wrinkles at the eye corners. However, these local facial parts contribute less in previous GAN based methods for age synthesis. To address this issue, we propose a Wavelet-domain Global and Local Consistent Age Generative Adversarial Network (WaveletGLCA-GAN), in which one global specific network and three local specific networks are integrated together to capture both global topology information and local texture details of human faces. Different from the most existing methods that modeling age synthesis in image-domain, we adopt wavelet transform to depict the textual information in frequency-domain. %Moreover, to achieve accurate age generation under the premise of preserving the identity information, age estimation network and face verification network are employed. Moreover, five types of losses are adopted: 1) adversarial loss aims to generate realistic wavelets; 2) identity preserving loss aims to better preserve identity information; 3) age preserving loss aims to enhance the accuracy of age synthesis; 4) pixel-wise loss aims to preserve the background information of the input face; 5) the total variation regularization aims to remove ghosting artifacts. Our method is evaluated on three face aging datasets, including CACD2000, Morph and FG-NET. Qualitative and quantitative experiments show the superiority of the proposed method over other state-of-the-arts.
Tasks	Age Estimation, Face Verification
Published	2018-09-20
URL	http://arxiv.org/abs/1809.07764v2
PDF	http://arxiv.org/pdf/1809.07764v2.pdf
PWC	https://paperswithcode.com/paper/global-and-local-consistent-wavelet-domain
Repo
Framework

The Impact of Annotation Guidelines and Annotated Data on Extracting App Features from App Reviews


Title	The Impact of Annotation Guidelines and Annotated Data on Extracting App Features from App Reviews
Authors	Faiz Ali Shah, Kairit Sirts, Dietmar Pfahl
Abstract	Annotation guidelines used to guide the annotation of training and evaluation datasets can have a considerable impact on the quality of machine learning models. In this study, we explore the effects of annotation guidelines on the quality of app feature extraction models. As a main result, we propose several changes to the existing annotation guidelines with a goal of making the extracted app features more useful and informative to the app developers. We test the proposed changes via simulating the application of the new annotation guidelines and then evaluating the performance of the supervised machine learning models trained on datasets annotated with initial and simulated guidelines. While the overall performance of automatic app feature extraction remains the same as compared to the model trained on the dataset with initial annotations, the features extracted by the model trained on the dataset with simulated new annotations are less noisy and more informative to the app developers. Secondly, we are interested in what kind of annotated training data is necessary for training an automatic app feature extraction model. In particular, we explore whether the training set should contain annotated app reviews from those apps/app categories on which the model is subsequently planned to be applied, or is it sufficient to have annotated app reviews from any app available for training, even when these apps are from very different categories compared to the test app. Our experiments show that having annotated training reviews from the test app is not necessary although including them into training set helps to improve recall. Furthermore, we test whether augmenting the training set with annotated product reviews helps to improve the performance of app feature extraction. We find that the models trained on augmented training set lead to improved recall but at the cost of the drop in precision.
Tasks
Published	2018-10-11
URL	http://arxiv.org/abs/1810.05187v1
PDF	http://arxiv.org/pdf/1810.05187v1.pdf
PWC	https://paperswithcode.com/paper/the-impact-of-annotation-guidelines-and
Repo
Framework

Privacy-Preserving Action Recognition for Smart Hospitals using Low-Resolution Depth Images


Title	Privacy-Preserving Action Recognition for Smart Hospitals using Low-Resolution Depth Images
Authors	Edward Chou, Matthew Tan, Cherry Zou, Michelle Guo, Albert Haque, Arnold Milstein, Li Fei-Fei
Abstract	Computer-vision hospital systems can greatly assist healthcare workers and improve medical facility treatment, but often face patient resistance due to the perceived intrusiveness and violation of privacy associated with visual surveillance. We downsample video frames to extremely low resolutions to degrade private information from surveillance videos. We measure the amount of activity-recognition information retained in low resolution depth images, and also apply a privately-trained DCSCN super-resolution model to enhance the utility of our images. We implement our techniques with two actual healthcare-surveillance scenarios, hand-hygiene compliance and ICU activity-logging, and show that our privacy-preserving techniques preserve enough information for realistic healthcare tasks.
Tasks	Activity Recognition, Super-Resolution, Temporal Action Localization
Published	2018-11-25
URL	http://arxiv.org/abs/1811.09950v1
PDF	http://arxiv.org/pdf/1811.09950v1.pdf
PWC	https://paperswithcode.com/paper/privacy-preserving-action-recognition-for
Repo
Framework