arXiv subjects

Nassir Navab

Publications and source records attributed to Nassir Navab.

At least 505 records · Page 28Linked to original sources

arXiv2018

Adversarial Semantic Scene Completion from a Single Depth Image

We propose a method to reconstruct, complete and semantically label a 3D scene from a single input depth image. We improve the accuracy of the regressed semantic 3D maps by a novel architecture based on adversarial learning. In particular, we suggest using multiple adversarial loss terms that not only enforce realistic outputs with respect to the ground truth, but also an effective embedding of the internal features. This is done by correlating the latent features of the encoder working on partial 2.5D data with the latent features extracted from a variational 3D auto-encoder trained to reconstruct the complete semantic scene. In addition, differently from other approaches that operate entirely through 3D convolutions, at test time we retain the original 2.5D structure of the input during downsampling to improve the effectiveness of the internal representation of our model. We test our approach on the main benchmark datasets for semantic scene completion to qualitatively and quantitatively assess the effectiveness of our proposal.

cs.CV↗

arXiv2018

The speaker-independent lipreading play-off; a survey of lipreading machines

Lipreading is a difficult gesture classification task. One problem in computer lipreading is speaker-independence. Speaker-independence means to achieve the same accuracy on test speakers not included in the training set as speakers within the training set. Current literature is limited on speaker-independent lipreading, the few independent test speaker accuracy scores are usually aggregated within dependent test speaker accuracies for an averaged performance. This leads to unclear independent results. Here we undertake a systematic survey of experiments with the TCD-TIMIT dataset using both conventional approaches and deep learning methods to provide a series of wholly speaker-independent benchmarks and show that the best speaker-independent machine scores 69.58% accuracy with CNN features and an SVM classifier. This is less than state of the art speaker-dependent lipreading machines, but greater than previously reported in independence experiments.

cs.CV↗

arXiv2018

Virtualization of tissue staining in digital pathology using an unsupervised deep learning approach

Histopathological evaluation of tissue samples is a key practice in patient diagnosis and drug development, especially in oncology. Historically, Hematoxylin and Eosin (H&E) has been used by pathologists as a gold standard staining. However, in many cases, various target specific stains, including immunohistochemistry (IHC), are needed in order to highlight specific structures in the tissue. As tissue is scarce and staining procedures are tedious, it would be beneficial to generate images of stained tissue virtually. Virtual staining could also generate in-silico multiplexing of different stains on the same tissue segment. In this paper, we present a sample application that generates FAP-CK virtual IHC images from Ki67-CD8 real IHC images using an unsupervised deep learning approach based on CycleGAN. We also propose a method to deal with tiling artifacts caused by normalization layers and we validate our approach by comparing the results of tissue analysis algorithms for virtual and real images.

cs.CV↗

arXiv2018

InfiNet: Fully Convolutional Networks for Infant Brain MRI Segmentation

We present a novel, parameter-efficient and practical fully convolutional neural network architecture, termed InfiNet, aimed at voxel-wise semantic segmentation of infant brain MRI images at iso-intense stage, which can be easily extended for other segmentation tasks involving multi-modalities. InfiNet consists of double encoder arms for T1 and T2 input scans that feed into a joint-decoder arm that terminates in the classification layer. The novelty of InfiNet lies in the manner in which the decoder upsamples lower resolution input feature map(s) from multiple encoder arms. Specifically, the pooled indices computed in the max-pooling layers of each of the encoder blocks are related to the corresponding decoder block to perform non-linear learning-free upsampling. The sparse maps are concatenated with intermediate encoder representations (skip connections) and convolved with trainable filters to produce dense feature maps. InfiNet is trained end-to-end to optimize for the Generalized Dice Loss, which is well-suited for high class imbalance. InfiNet achieves the whole-volume segmentation in under 50 seconds and we demonstrate competitive performance against multiple state-of-the art deep architectures and their multi-modal variants.

cs.CV↗

arXiv2018

Deep Model-Based 6D Pose Refinement in RGB

We present a novel approach for model-based 6D pose refinement in color data. Building on the established idea of contour-based pose tracking, we teach a deep neural network to predict a translational and rotational update. At the core, we propose a new visual loss that drives the pose update by aligning object contours, thus avoiding the definition of any explicit appearance model. In contrast to previous work our method is correspondence-free, segmentation-free, can handle occlusion and is agnostic to geometrical symmetry as well as visual ambiguities. Additionally, we observe a strong robustness towards rough initialization. The approach can run in real-time and produces pose accuracies that come close to 3D ICP without the need for depth data. Furthermore, our networks are trained from purely synthetic data and will be published together with the refinement code to ensure reproducibility.

cs.CV↗

arXiv2018

Weakly-Supervised Localization and Classification of Proximal Femur Fractures

In this paper, we target the problem of fracture classification from clinical X-Ray images towards an automated Computer Aided Diagnosis (CAD) system. Although primarily dealing with an image classification problem, we argue that localizing the fracture in the image is crucial to make good class predictions. Therefore, we propose and thoroughly analyze several schemes for simultaneous fracture localization and classification. We show that using an auxiliary localization task, in general, improves the classification performance. Moreover, it is possible to avoid the need for additional localization annotations thanks to recent advancements in weakly-supervised deep learning approaches. Among such approaches, we investigate and adapt Spatial Transformers (ST), Self-Transfer Learning (STL), and localization from global pooling layers. We provide a detailed quantitative and qualitative validation on a dataset of 1347 femur fractures images and report high accuracy with regard to inter-expert correlation values reported in the literature. Our investigations show that i) lesion localization improves the classification outcome, ii) weakly-supervised methods improve baseline classification without any additional cost, iii) STL guides feature activations and boost performance. We plan to make both the dataset and code available.

cs.CV↗

arXiv2018

Incremental Adversarial Learning for Optimal Path Planning

Path planning plays an essential role in many areas of robotics. Various planning techniques have been presented, either focusing on learning a specific task from demonstrations or retrieving trajectories by optimizing for hand-crafted cost functions which are well defined a priori. In this work, we present an incremental adversarial learning-based framework that allows inferring implicit behaviour, i.e. the natural characteristic of a set of given trajectories. To achieve adversarial learning, a zero-sum game is constructed between a planning algorithm and an adversary - the discriminator. We employ the discriminator within an optimal motion planning algorithm, such that costs can be learned and optimized iteratively, improving the integration of implicit behavior. By combining a cost-based planning approach with trained intrinsic behaviour, this can be be integrated also with other constraints such as obstacles or general cost factors within a single planning framework. We demonstrate the proposed method on a dataset for collision avoidance, as well as for the generation of human-like trajectories from motion capture data. Our results show that incremental adversarial learning is able to generate paths that reflect the natural implicit behaviour of a dataset, with the ability to improve on performance using iterative learning and generation.

cs.RO↗

arXiv2018

Generalizing multistain immunohistochemistry tissue segmentation using one-shot color deconvolution deep neural networks

A key challenge in cancer immunotherapy biomarker research is quantification of pattern changes in microscopic whole slide images of tumor biopsies. Different cell types tend to migrate into various tissue compartments and form variable distribution patterns. Drug development requires correlative analysis of various biomarkers in and between the tissue compartments. To enable that, tissue slides are manually annotated by expert pathologists. Manual annotation of tissue slides is a labor intensive, tedious and error-prone task. Automation of this annotation process can improve accuracy and consistency while reducing workload and cost in a way that will positively influence drug development efforts. In this paper we present a novel one-shot color deconvolution deep learning method to automatically segment and annotate digitized slide images with multiple stainings into compartments of tumor, healthy tissue, and necrosis. We address the task in the context of drug development where multiple stains, tissue and tumor types exist and look into solutions for generalizations over these image populations.

cs.CV↗

arXiv2018

Generating Highly Realistic Images of Skin Lesions with GANs

As many other machine learning driven medical image analysis tasks, skin image analysis suffers from a chronic lack of labeled data and skewed class distributions, which poses problems for the training of robust and well-generalizing models. The ability to synthesize realistic looking images of skin lesions could act as a reliever for the aforementioned problems. Generative Adversarial Networks (GANs) have been successfully used to synthesize realistically looking medical images, however limited to low resolution, whereas machine learning models for challenging tasks such as skin lesion segmentation or classification benefit from much higher resolution data. In this work, we successfully synthesize realistically looking images of skin lesions with GANs at such high resolution. Therefore, we utilize the concept of progressive growing, which we both quantitatively and qualitatively compare to other GAN architectures such as the DCGAN and the LAPGAN. Our results show that with the help of progressive growing, we can synthesize highly realistic dermoscopic images of skin lesions that even expert dermatologists find hard to distinguish from real ones.

cs.CV↗

arXiv2018

Recalibrating Fully Convolutional Networks with Spatial and Channel 'Squeeze & Excitation' Blocks

In a wide range of semantic segmentation tasks, fully convolutional neural networks (F-CNNs) have been successfully leveraged to achieve state-of-the-art performance. Architectural innovations of F-CNNs have mainly been on improving spatial encoding or network connectivity to aid gradient flow. In this article, we aim towards an alternate direction of recalibrating the learned feature maps adaptively; boosting meaningful features while suppressing weak ones. The recalibration is achieved by simple computational blocks that can be easily integrated in F-CNNs architectures. We draw our inspiration from the recently proposed 'squeeze & excitation' (SE) modules for channel recalibration for image classification. Towards this end, we introduce three variants of SE modules for segmentation, (i) squeezing spatially and exciting channel-wise, (ii) squeezing channel-wise and exciting spatially and (iii) joint spatial and channel 'squeeze & excitation'. We effectively incorporate the proposed SE blocks in three state-of-the-art F-CNNs and demonstrate a consistent improvement of segmentation accuracy on three challenging benchmark datasets. Importantly, SE blocks only lead to a minimal increase in model complexity of about 1.5%, while the Dice score increases by 4-9% in the case of U-Net. Hence, we believe that SE blocks can be an integral part of future F-CNN architectures.

cs.CV↗

arXiv2018

Fully-Convolutional Point Networks for Large-Scale Point Clouds

This work proposes a general-purpose, fully-convolutional network architecture for efficiently processing large-scale 3D data. One striking characteristic of our approach is its ability to process unorganized 3D representations such as point clouds as input, then transforming them internally to ordered structures to be processed via 3D convolutions. In contrast to conventional approaches that maintain either unorganized or organized representations, from input to output, our approach has the advantage of operating on memory efficient input data representations while at the same time exploiting the natural structure of convolutional operations to avoid the redundant computing and storing of spatial information in the network. The network eliminates the need to pre- or post process the raw sensor data. This, together with the fully-convolutional nature of the network, makes it an end-to-end method able to process point clouds of huge spaces or even entire rooms with up to 200k points at once. Another advantage is that our network can produce either an ordered output or map predictions directly onto the input cloud, thus making it suitable as a general-purpose point cloud descriptor applicable to many 3D tasks. We demonstrate our network's ability to effectively learn both low-level features as well as complex compositional relationships by evaluating it on benchmark datasets for semantic voxel segmentation, semantic part segmentation and 3D scene captioning.

cs.CV↗

arXiv2018

Deep Learned Full-3D Object Completion from Single View

3D geometry is a very informative cue when interacting with and navigating an environment. This writing proposes a new approach to 3D reconstruction and scene understanding, which implicitly learns 3D geometry from depth maps pairing a deep convolutional neural network architecture with an auto-encoder. A data set of synthetic depth views and voxelized 3D representations is built based on ModelNet, a large-scale collection of CAD models, to train networks. The proposed method offers a significant advantage over current, explicit reconstruction methods in that it learns key geometric features offline and makes use of those to predict the most probable reconstruction of an unseen object. The relatively small network, consisting of roughly 4 million weights, achieves a 92.9% reconstruction accuracy at a 30x30x30 resolution through the use of a pre-trained decompression layer. This is roughly 1/4 the weights of the current leading network. The fast execution time of the model makes it suitable for real-time applications.

cs.CV↗

arXiv2018

Towards Robotic Eye Surgery: Marker-free, Online Hand-eye Calibration using Optical Coherence Tomography Images

Ophthalmic microsurgery is known to be a challenging operation, which requires very precise and dexterous manipulation. Image guided robot-assisted surgery (RAS) is a promising solution that brings significant improvements in outcomes and reduces the physical limitations of human surgeons. However, this technology must be further developed before it can be routinely used in clinics. One of the problems is the lack of proper calibration between the robotic manipulator and appropriate imaging device. In this work, we developed a flexible framework for hand-eye calibration of an ophthalmic robot with a microscope-integrated Optical Coherence Tomography (MIOCT) without any markers. The proposed method consists of three main steps: a) we estimate the OCT calibration parameters; b) with micro-scale displacements controlled by the robot, we detect and segment the needle tip in 3D-OCT volume; c) we find the transformation between the coordinate system of the OCT camera and the coordinate system of the robot. We verified the capability of our framework in ex-vivo pig eye experiments and compared the results with a reference method (marker-based). In all experiments, our method showed a small difference from the marker based method, with a mean calibration error of 9.2 $μ$m and 7.0 $μ$m, respectively. Additionally, the noise test shows the robustness of the proposed method.

cs.RO↗

arXiv2018

Human Motion Analysis with Deep Metric Learning

Effectively measuring the similarity between two human motions is necessary for several computer vision tasks such as gait analysis, person identi- fication and action retrieval. Nevertheless, we believe that traditional approaches such as L2 distance or Dynamic Time Warping based on hand-crafted local pose metrics fail to appropriately capture the semantic relationship across motions and, as such, are not suitable for being employed as metrics within these tasks. This work addresses this limitation by means of a triplet-based deep metric learning specifically tailored to deal with human motion data, in particular with the prob- lem of varying input size and computationally expensive hard negative mining due to motion pair alignment. Specifically, we propose (1) a novel metric learn- ing objective based on a triplet architecture and Maximum Mean Discrepancy; as well as, (2) a novel deep architecture based on attentive recurrent neural networks. One benefit of our objective function is that it enforces a better separation within the learned embedding space of the different motion categories by means of the associated distribution moments. At the same time, our attentive recurrent neural network allows processing varying input sizes to a fixed size of embedding while learning to focus on those motion parts that are semantically distinctive. Our ex- periments on two different datasets demonstrate significant improvements over conventional human motion metrics.

cs.CV↗

arXiv2018

Scene Coordinate and Correspondence Learning for Image-Based Localization

Scene coordinate regression has become an essential part of current camera re-localization methods. Different versions, such as regression forests and deep learning methods, have been successfully applied to estimate the corresponding camera pose given a single input image. In this work, we propose to regress the scene coordinates pixel-wise for a given RGB image by using deep learning. Compared to the recent methods, which usually employ RANSAC to obtain a robust pose estimate from the established point correspondences, we propose to regress confidences of these correspondences, which allows us to immediately discard erroneous predictions and improve the initial pose estimates. Finally, the resulting confidences can be used to score initial pose hypothesis and aid in pose refinement, offering a generalized solution to solve this task.

cs.CV↗

arXiv2018

Peeking Behind Objects: Layered Depth Prediction from a Single Image

While conventional depth estimation can infer the geometry of a scene from a single RGB image, it fails to estimate scene regions that are occluded by foreground objects. This limits the use of depth prediction in augmented and virtual reality applications, that aim at scene exploration by synthesizing the scene from a different vantage point, or at diminished reality. To address this issue, we shift the focus from conventional depth map prediction to the regression of a specific data representation called Layered Depth Image (LDI), which contains information about the occluded regions in the reference frame and can fill in occlusion gaps in case of small view changes. We propose a novel approach based on Convolutional Neural Networks (CNNs) to jointly predict depth maps and foreground separation masks used to condition Generative Adversarial Networks (GANs) for hallucinating plausible color and depths in the initially occluded areas. We demonstrate the effectiveness of our approach for novel scene view synthesis from a single image.

cs.CV↗

arXiv2018

Competition vs. Concatenation in Skip Connections of Fully Convolutional Networks

Increased information sharing through short and long-range skip connections between layers in fully convolutional networks have demonstrated significant improvement in performance for semantic segmentation. In this paper, we propose Competitive Dense Fully Convolutional Networks (CDFNet) by introducing competitive maxout activations in place of naive feature concatenation for inducing competition amongst layers. Within CDFNet, we propose two architectural contributions, namely competitive dense block (CDB) and competitive unpooling block (CUB) to induce competition at local and global scales for short and long-range skip connections respectively. This extension is demonstrated to boost learning of specialized sub-networks targeted at segmenting specific anatomies, which in turn eases the training of complex tasks. We present the proof-of-concept on the challenging task of whole body segmentation in the publicly available VISCERAL benchmark and demonstrate improved performance over multiple learning and registration based state-of-the-art methods.

cs.CV↗

arXiv2018

SynNet: Structure-Preserving Fully Convolutional Networks for Medical Image Synthesis

Cross modal image syntheses is gaining significant interests for its ability to estimate target images of a different modality from a given set of source images,like estimating MR to MR, MR to CT, CT to PET etc, without the need for an actual acquisition.Though they show potential for applications in radiation therapy planning,image super resolution, atlas construction, image segmentation etc.The synthesis results are not as accurate as the actual acquisition.In this paper,we address the problem of multi modal image synthesis by proposing a fully convolutional deep learning architecture called the SynNet.We extend the proposed architecture for various input output configurations. And finally, we propose a structure preserving custom loss function for cross-modal image synthesis.We validate the proposed SynNet and its extended framework on BRATS dataset with comparisons against three state-of-the art methods.And the results of the proposed custom loss function is validated against the traditional loss function used by the state-of-the-art methods for cross modal image synthesis.

cs.CV↗