Publications

Topics:
  1. E. Schwartz, L. Karlinsky, J. Shtok, S. Harary, M. Marder, R. Feris, A. Kumar, R. Giryes, A. M. Bronstein, ∆-encoder: an effective sample synthesis method for few-shot object recognition, Proc. Neural Information Processing Systems (NIPS), 2018 details

    ∆-encoder: an effective sample synthesis method for few-shot object recognition

    E. Schwartz, L. Karlinsky, J. Shtok, S. Harary, M. Marder, R. Feris, A. Kumar, R. Giryes, A. M. Bronstein
    Proc. Neural Information Processing Systems (NIPS), 2018

    Learning to classify new categories based on just one or a few examples is a long-standing challenge in modern computer vision. In this work, we propose a simple yet effective method for few-shot (and one-shot) object recognition. Our approach is based on a modified auto-encoder, denoted ∆-encoder, that learns to synthesize new samples for an unseen category just by seeing few examples from it. The synthesized samples are then used to train a classifier. The proposed approach learns to both extract transferable intra-class deformations, or “deltas”, between same-class pairs of training examples, and to apply those deltas to the few provided examples of a novel class (unseen during training) in order to efficiently synthesize samples from that new class. The proposed method improves over the state-of-the-art in one-shot object-recognition and compares favorably in the few-shot case.

    E. Rodolà, Z. Lähner, A. M. Bronstein, M. M. Bronstein, J. Solomon, Functional maps representation on product manifolds, arXiv:1809.10940, 2018 details

    Functional maps representation on product manifolds

    E. Rodolà, Z. Lähner, A. M. Bronstein, M. M. Bronstein, J. Solomon
    arXiv:1809.10940, 2018

    We consider the tasks of representing, analyzing and manipulating maps between shapes. We model maps as densities over the product manifold of the input shapes; these densities can be treated as scalar functions and therefore are manipulable using the language of signal processing on manifolds. Being a manifold itself, the product space endows the set of maps with a geometry of its own, which we exploit to define map operations in the spectral domain; we also derive relationships with other existing representations (soft maps and functional maps). To apply these ideas in practice, we discretize product manifolds and their Laplace-Beltrami operators, and we introduce localized spectral analysis of the product manifold as a novel tool for map processing. Our framework applies to maps defined between and across 2D and 3D shapes without requiring special adjustment, and it can be implemented efficiently with simple operations on sparse matrices.

    C. Baskin, N. Liss, Y. Chai, E. Zheltonozhskii, E. Schwartz, R. Giryes, A. Mendelson, A. M. Bronstein, NICE: noise injection and clamping estimation for neural network quantization, arXiv:1810.00162, 2018 details

    NICE: noise injection and clamping estimation for neural network quantization

    C. Baskin, N. Liss, Y. Chai, E. Zheltonozhskii, E. Schwartz, R. Giryes, A. Mendelson, A. M. Bronstein
    arXiv:1810.00162, 2018

    Convolutional Neural Networks (CNN) are very popular in many fields including computer vision, speech recognition, natural language processing, to name a few. Though deep learning leads to groundbreaking performance in these domains, the networks used are very demanding computationally and are far from real-time even on a GPU, which is not power efficient and therefore does not suit low power systems such as mobile devices. To overcome this challenge, some solutions have been proposed for quantizing the weights and activations of these networks, which accelerate the runtime significantly. Yet, this acceleration comes at the cost of a larger error. The uniqname method proposed in this work trains quantized neural networks by noise injection and a learned clamping, which improve the accuracy. This leads to state-of-the-art results on various regression and classification tasks, e.g., ImageNet classification with architectures such as ResNet-18/34/50 with low as 3-bit weights and activations. We implement the proposed solution on an FPGA to demonstrate its applicability for low power real-time applications.

    Q. Qiu, J. Lezama, A. M. Bronstein, G. Sapiro, ForestHash: Semantic hashing with shallow random forests and tiny convolutional networks, Proc. European Conf. on Computer Vision (ECCV), 2018 details

    ForestHash: Semantic hashing with shallow random forests and tiny convolutional networks

    Q. Qiu, J. Lezama, A. M. Bronstein, G. Sapiro
    Proc. European Conf. on Computer Vision (ECCV), 2018

    Hash codes are efficient data representations for coping with the ever growing amounts of data. In this paper, we introduce a random forest semantic hashing scheme that embeds tiny convolutional neural networks (CNN) into shallow random forests, with near-optimal information-theoretic code aggregation among trees. We start with a simple hashing scheme, where random trees in a forest act as hashing functions by setting `1′ for the visited tree leaf, and `0′ for the rest. We show that traditional random forests fail to generate hashes that preserve the underlying similarity between the trees, rendering the random forests approach to hashing challenging. To address this, we propose to first randomly group arriving classes at each tee split node into two groups, obtaining a significantly simplified two-class classification problem, which can be handled using a light-weight CNN weak learner. Such random class grouping scheme enables code uniqueness by enforcing each class to share its code with different classes in different trees. A non-conventional low-rank loss is further adopted for the CNN weak learners to encourage code consistency by minimizing intra-class variations and maximizing inter-class distance for the two random class groups. Finally, we introduce an information-theoretic approach for aggregating codes of individual trees into a single hash code, producing a near-optimal unique hash for each class. The proposed approach significantly outperforms state-of-the-art hashing methods for image retrieval tasks on large-scale public datasets, while performing at the level of other state-of-the-art image classification techniques while utilizing a more compact and efficient scalable representation. This work proposes a principled and robust procedure to train and deploy in parallel an ensemble of light-weight CNNs, instead of simply going deeper.

    T. Remez, O. Litany, R. Giryes, A. M. Bronstein, Class-aware fully-convolutional Gaussian and Poisson denoising, IEEE Trans. Image Processing, Vol. 27(11), 2018 details

    Class-aware fully-convolutional Gaussian and Poisson denoising

    T. Remez, O. Litany, R. Giryes, A. M. Bronstein
    IEEE Trans. Image Processing, Vol. 27(11), 2018

    We propose a fully-convolutional neural-network architecture for image denoising which is simple yet powerful. Its structure allows to exploit the gradual nature of the denoising process, in which shallow layers handle local noise statistics, while deeper layers recover edges and enhance textures. Our method advances the state-of-the-art when trained for different noise levels and distributions (both Gaussian and Poisson). In addition, we show that making the denoiser class-aware by exploiting semantic class information boosts performance, enhances textures and reduces artifacts.

    A. Tsitsulin, D. Mottin, P. Karras, A. M. Bronstein, E, Mueller, NetLSD: Hearing the shape of a graph, Proc. ACM Special Interest Group on Knowledge Discovery and Data Mining (SIGKDD), 2018 details

    NetLSD: Hearing the shape of a graph

    A. Tsitsulin, D. Mottin, P. Karras, A. M. Bronstein, E, Mueller
    Proc. ACM Special Interest Group on Knowledge Discovery and Data Mining (SIGKDD), 2018

    Comparison among graphs is ubiquitous in graph analytics. However, it is a hard task in terms of the expressiveness of the employed similarity measure and the efficiency of its computation. Ideally, graph comparison should be invariant to the order of nodes and the sizes of compared graphs, adaptive to the scale of graph patterns, and scalable. Unfortunately, these properties have not been addressed together. Graph comparisons still rely on direct approaches, graph kernels, or representation-based methods, which are all inefficient and impractical for large graph collections. In this paper, we propose the Network Laplacian Spectral Descriptor (NetLSD): the first, to our knowledge, permutation- and size-invariant, scale-adaptive, and efficiently computable graph representation method that allows for straightforward comparisons of large graphs. NetLSD extracts a compact signature that inherits the formal properties of the Laplacian spectrum, specifically its heat or wave kernel; thus, it hears the shape of a graph. Our evaluation on a variety of real-world graphs demonstrates that it outperforms previous works in both expressiveness and efficiency.

    O. Senouf, S. Vedula, G. Zurakhov, A. M. Bronstein, M. Zibulevsky, O. Michailovich, D. Adam, D. Blondheim, High frame-rate cardiac ultrasound imaging with deep learning, Proc. Int'l Conf. Medical Image Computing & Computer Assisted Intervention (MICCAI), 2018 details

    High frame-rate cardiac ultrasound imaging with deep learning

    O. Senouf, S. Vedula, G. Zurakhov, A. M. Bronstein, M. Zibulevsky, O. Michailovich, D. Adam, D. Blondheim
    Proc. Int'l Conf. Medical Image Computing & Computer Assisted Intervention (MICCAI), 2018

    Cardiac ultrasound imaging requires a high frame rate in order to capture rapid motion. This can be achieved by multi-line acquisition (MLA), where several narrow-focused received lines are obtained from each wide-focused transmitted line. This shortens the acquisition time at the expense of introducing block artifacts. In this paper, we propose a data-driven learning-based approach to improve the MLA image quality. We train an end-to-end convolutional neural network on pairs of real ultrasound cardiac data, acquired through MLA and the corresponding single-line acquisition (SLA). The network achieves a significant improvement in image quality for both 5- and 7-line MLA resulting in a decorrelation measure similar to that of SLA while having the frame rate of MLA.

    S. Vedula, O. Senouf, G. Zurakhov, A. M. Bronstein, M. Zibulevsky, O. Michailovich, D. Adam, D. Gaitini, High quality ultrasonic multi-line transmission through deep learning, Proc. Machine Learning for Medical Image Reconstruction (MLMIR), 2018 details

    High quality ultrasonic multi-line transmission through deep learning

    S. Vedula, O. Senouf, G. Zurakhov, A. M. Bronstein, M. Zibulevsky, O. Michailovich, D. Adam, D. Gaitini
    Proc. Machine Learning for Medical Image Reconstruction (MLMIR), 2018

    Frame rate is a crucial consideration in cardiac ultrasound imaging and 3D sonography. Several methods have been proposed in the medical ultrasound literature aiming at accelerating the image acquisition. In this paper, we consider one such method called multi-line transmission (MLT), in which several evenly separated focused beams are transmitted simultaneously. While MLT reduces the acquisition time, it comes at the expense of a heavy loss of contrast due to the interactions between the beams (cross-talk artifact). In this paper, we introduce a data-driven method to reduce the artifacts arising in MLT. To this end, we propose to train an end-to-end convolutional neural network consisting of correction layers followed by a constant apodization layer. The network is trained on pairs of raw data obtained through MLT and the corresponding single-line transmission (SLT) data. Experimental evaluation demonstrates signi cant improvement both in the visual image quality and in objective measures such as contrast ratio and contrast-to-noise ratio, while preserving resolution unlike traditional apodization-based methods. We show that the proposed method is able to generalize
    well across di erent patients and anatomies on real and phantom data.

    A. Tsitsulin, D. Mottin, P. Karras, A. M. Bronstein, E, Mueller, SGR: Self-supervised spectral graph representation learning, Proc. KDD Deep Learning Day, 2018 details

    SGR: Self-supervised spectral graph representation learning

    A. Tsitsulin, D. Mottin, P. Karras, A. M. Bronstein, E, Mueller
    Proc. KDD Deep Learning Day, 2018

    Representing a graph as a vector is a challenging task; ideally, the representation should be easily computable and conducive to efficient comparisons among graphs, tailored to the particular data and an analytical task at hand. Unfortunately, a “one-size-fits-all” solution is unattainable, as different analytical tasks may require different attention to global or local graph features. We develop SGR, the first, to our knowledge, method for learning graph representations in a self-supervised manner. Grounded on spectral graph analysis, SGR seamlessly combines all aforementioned desirable properties. In extensive experiments, we show how our approach works on large graph collections, facilitates self-supervised representation learning across a variety of application domains, and performs competitively to state-of-the-art methods without re-training.

    E. Schwartz, R. Giryes, A. M. Bronstein, DeepISP: Towards learning an end-to-end image processing pipeline, IEEE Trans. on Image Processing, 2018 details

    DeepISP: Towards learning an end-to-end image processing pipeline

    E. Schwartz, R. Giryes, A. M. Bronstein
    IEEE Trans. on Image Processing, 2018

    We present DeepISP, a full end-to-end deep neural model of the camera image signal processing (ISP) pipeline. Our model learns a mapping from the raw low-light mosaiced image to the final visually compelling image and encompasses low-level tasks such as demosaicing and denoising as well as higher-level tasks such as color correction and image adjustment. The training and evaluation of the pipeline were performed on a dedicated dataset containing pairs of low-light and well-lit images captured by a Samsung S7 smartphone camera in both raw and processed JPEG formats. The proposed solution achieves state-of-the-art performance in the objective evaluation of PSNR on the subtask of joint denoising and demosaicing. For the full end-to-end pipeline, it achieves better visual quality compared to the manufacturer ISP, in both a subjective human assessment and when rated by a deep model trained for assessing image quality.

    H. Haim, S. Elmalem, R. Giryes, A. M. Bronstein, E. Marom, Depth estimation from a single image using deep learned phase coded mask, IEEE Trans. Computational Imaging, Vol. 2(3), 2018 (Winner of the OSA Student Grand Challenge The Optical System of the Future) details

    Depth estimation from a single image using deep learned phase coded mask

    H. Haim, S. Elmalem, R. Giryes, A. M. Bronstein, E. Marom
    IEEE Trans. Computational Imaging, Vol. 2(3), 2018 (Winner of the OSA Student Grand Challenge The Optical System of the Future)

    Depth estimation from a single image is a well-known challenge in computer vision. With the advent of deep learning, several approaches for monocular depth estimation have been proposed, all of which have inherent limitations due to the scarce depth cues that exist in a single image. Moreover, these methods are very demanding computationally, which makes them inadequate for systems with limited processing power. In this paper, a phase-coded aperture camera for depth estimation is proposed. The camera is equipped with an optical phase mask that provides unambiguous depth-related color characteristics for the captured image. These are used for estimating the scene depth map using a fully convolutional neural network. The phase-coded aperture structure is learned jointly with the network weights using backpropagation. The strong depth cues (encoded in the image by the phase mask, designed together with the network weights) allow a much simpler neural network architecture for faster and more accurate depth estimation. Performance achieved on simulated images as well as on a real optical setup is superior to the state-of-the-art monocular depth estimation methods (both with respect to the depth accuracy and required processing power), and is competitive with more complex and expensive depth estimation methods such as light-field cameras.

    E. Tsitsin, A. M. Bronstein, T. Hendler, M. Medvedovsky, Passive electric impedance tomography, Proc. Electric Impedance Tomography (EIT), 2018 details

    Passive electric impedance tomography

    E. Tsitsin, A. M. Bronstein, T. Hendler, M. Medvedovsky
    Proc. Electric Impedance Tomography (EIT), 2018

    We introduce an electric impedance tomography modality without any active current injection. By loading the probe electrodes with a time-varying network of impedances, the proposed technique exploits electrical fields existing in the medium due to biological activity or EM interference from the environment or an implantable device. A phantom validation of the technique is presented.

    E. Tsitsin, T. Mund, A. M. Bronstein, Printable anisotropic phantom for EEG with distributed current sources, Proc. IEEE Int'l Symposium on Biomedical Imaging (ISBI), 2018 details

    Printable anisotropic phantom for EEG with distributed current sources

    E. Tsitsin, T. Mund, A. M. Bronstein
    Proc. IEEE Int'l Symposium on Biomedical Imaging (ISBI), 2018

    We introduce an electric impedance tomography modality without any active current injection. By loading the probe electrodes with a time-varying network of impedances, the proposed technique exploits electrical fields existing in the medium due to biological activity or EM interference from the environment or an implaPresented is the phantom mimicking the electromagnetic properties of the human head. The fabrication is based on the additive manufacturing (3d-printing) technology combined with the electrically conductive gel. The novel key features of the phantom are the controllable anisotropic electrical conductivity of the skull and the densely packed actively multiplexed monopolar current sources permitting interpolation of the measured gain function to any dipolar current source position and orientation within the head. The phantom was tested in realistic environment successfully simulating the possible signals from neural activations situated at any depth within the brain as well as EMI and motion artifacts. The proposed design can be readily repeated in any lab having an access to a standard 100 micron precision 3d-printer. The meshes of the phantom are available from the corresponding author.ntable device. A phantom validation of the technique is presented.

    E. Tsitsin, M. Medvedovsky, A. M. Bronstein, VibroEEG: Improved EEG source reconstruction by combined acoustic-electric imaging, Proc. IEEE Int'l Symposium on Biomedical Imaging (ISBI), 2018 details

    VibroEEG: Improved EEG source reconstruction by combined acoustic-electric imaging

    E. Tsitsin, M. Medvedovsky, A. M. Bronstein
    Proc. IEEE Int'l Symposium on Biomedical Imaging (ISBI), 2018

    Electroencephalography (EEG) is the electrical neural activity recording modality with high temporal and low spatial resolution. Here we propose a novel technique that we call vibroEEG improving significantly the source localization accuracy of EEG. Our method combines electric potential acquisition in concert with acoustic excitation of the vibrational modes of the electrically active cerebral cortex which displace periodically the sources of the low frequency neural electrical activity. The sources residing on the maxima of the induced modes will be maximally weighted in the corresponding spectral components of the broadband signals measured on the noninvasive electrodes. In vibroEEG, for the first time the rich internal geometry of the cerebral cortex can be utilized to separate sources of neural activity lying close in the sense of the Euclidean metric. When the modes are excited locally using phased arrays the neural activity can essentially be probed at any cortical location. When a single transducer is used to induce the excitations, the EEG gain matrix is still being enriched with numerous independent gain vectors increasing its rank. We show theoretically and on numerical simulation that in both cases the source localization accuracy improves substantially.

    C. Baskin, N. Liss, E. Zheltonozhskii, A. M. Bronstein, A. Mendelson, Streaming architectures for large-scale quantized neural networks on an FPGA-based dataflow platform, IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), 2018 details

    Streaming architectures for large-scale quantized neural networks on an FPGA-based dataflow platform

    C. Baskin, N. Liss, E. Zheltonozhskii, A. M. Bronstein, A. Mendelson
    IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), 2018

    Deep neural networks (DNNs) are used by different applications that are executed on a range of computer architectures, from IoT devices to supercomputers. The footprint of these networks is huge as well as their computational and communication needs. In order to ease the pressure on resources, research indicates that in many cases a low precision representation (1-2 bit per parameter) of weights and other parameters can achieve similar accuracy while requiring less resources. Using quantized values enables the use of FPGAs to run NNs, since FPGAs are well fitted to these primitives; e.g., FPGAs provide efficient support for bitwise operations and can work with arbitrary-precision representation of numbers. This paper presents a new streaming architecture for running QNNs on FPGAs. The proposed architecture scales out better than alternatives, allowing us to take advantage of systems with multiple FPGAs. We also included support for skip connections, that are used in state-of-the art NNs, and shown that our architecture allows to add those connections almost for free. All this allowed us to implement an 18-layer ResNet for 224×224 images classification, achieving 57.5% top-1 accuracy. In addition, we implemented a full-sized quantized AlexNet. In contrast to previous works, we use 2-bit activations instead of 1-bit ones, which improves AlexNet’s top-1 accuracy from 41.8% to 51.03% for the ImageNet classification. Both AlexNet and ResNet can handle 1000-class real-time classification on an FPGA. Our implementation of ResNet-18 consumes 5× less power and is 4× slower for ImageNet, when compared to the same NN on the latest Nvidia GPUs. Smaller NNs, that fit a single FPGA, are running faster then on GPUs on small (32×32) inputs, while consuming up to 20× less energy and power.

    C. Baskin, E. Schwartz, E. Zheltonozhskii, N. Liss, R. Giryes, A. M. Bronstein, A. Mendelson, UNIQ: Uniform noise injection for non-uniform quantization of neural networks, arXiv:1804.10969, 2018 details

    UNIQ: Uniform noise injection for non-uniform quantization of neural networks

    C. Baskin, E. Schwartz, E. Zheltonozhskii, N. Liss, R. Giryes, A. M. Bronstein, A. Mendelson
    arXiv:1804.10969, 2018

    We present a novel method for training a neural network amenable to inference in low-precision arithmetic with quantized weights and activations. The training is performed in full precision with random noise injection emulating quantization noise. In order to circumvent the need to simulate realistic quantization noise distributions, the weight distributions are uniformized by a non-linear transfor- mation, and uniform noise is injected. This procedure emulates a non-uniform k-quantile quantizer at inference time, which adapts to the specific distribution of the quantized parameters. As a by-product of injecting noise to weights, we find that activations can also be quantized to as low as 8-bit with only a minor accuracy degradation. The method achieves state-of-the-art results for training low-precision networks on ImageNet. In particular, we observe no degradation in accuracy for MobileNet and ResNet-18/34/50 on ImageNet with as low as 4-bit quantization of weights. Our solution achieves the state-of-the-art results in accuracy, in the low computational budget regime, compared to similar models.

    R. Giryes, Y. C. Eldar, A. M. Bronstein, G. Sapiro, Tradeoffs between convergence speed and reconstruction accuracy in inverse problems, IEEE Trans. on Signal Processing, Vol. 66(7), 2018 details

    Tradeoffs between convergence speed and reconstruction accuracy in inverse problems

    R. Giryes, Y. C. Eldar, A. M. Bronstein, G. Sapiro
    IEEE Trans. on Signal Processing, Vol. 66(7), 2018

    Solving inverse problems with iterative algorithms is popular, especially for large data. Due to time constraints, the number of possible iterations is usually limited, potentially affecting the achievable accuracy. Given an error one is willing to tolerate, an important question is whether it is possible to modify the original iterations to obtain faster convergence to a minimizer achieving the allowed error without increasing the computational cost of each iteration considerably. Relying on recent recovery techniques developed for settings in which the desired signal belongs to some low-dimensional set, we show that using a coarse estimate of this set may lead to faster convergence at the cost of an additional reconstruction error related to the accuracy of the set approximation. Our theory ties to recent advances in sparse recovery, compressed sensing, and deep learning. Particularly, it may provide a possible explanation to the successful approximation of the L1-minimization solution by neural networks with layers representing iterations, as practiced in the learned iterative shrinkage-thresholding algorithm.