Publications

Topics:
  1. Q. Qiu, G. Sapiro, A. M. Bronstein, Random forests can hash, arXiv:1412.5083 details

    Random forests can hash

    Q. Qiu, G. Sapiro, A. M. Bronstein
    arXiv:1412.5083

    Hash codes are a very efficient data representation needed to be able to cope with the ever growing amounts of data. We introduce a random forest semantic hashing scheme with information-theoretic code aggregation, showing for the first time how random forest, a technique that together with deep learning have shown spectacular results in classification, can also be extended to large-scale retrieval. Traditional random forest fails to enforce the consistency of hashes generated from each tree for the same class data, i.e., to preserve the underlying similarity, and it also lacks a principled way for code aggregation across trees. We start with a simple hashing scheme, where independently trained random trees in a forest are acting as hashing functions. We the propose a subspace model as the splitting function, and show that it enforces the hash consistency in a tree for data from the same class. We also 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. Experiments on large-scale public datasets are presented, showing that the proposed approach significantly outperforms state-of-the-art hashing methods for retrieval tasks.

    P. Sprechmann, A. M. Bronstein, G. Sapiro, Supervised non-Euclidean sparse NMF via bilevel optimization with applications to speech enhancement, Proc. Joint Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA), 2014 details

    Supervised non-Euclidean sparse NMF via bilevel optimization with applications to speech enhancement

    P. Sprechmann, A. M. Bronstein, G. Sapiro
    Proc. Joint Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA), 2014

    Traditionally, NMF algorithms consist of two separate stages: a training stage, in which a generative model is learned; and a testing stage in which the pre-learned model is used in a high level task such as enhancement, separation, or classification. As an alternative, we propose a task-supervised NMF method for the adaptation of the basis spectra learned in the first stage to enhance the performance on the specific task used in the second stage. We cast this problem as a bilevel optimization program that can be efficiently solved via stochastic gradient descent. The proposed approach is general enough to handle sparsity priors of the activations, and allow non-Euclidean data terms such as beta-divergences. The framework is evaluated on single-channel speech enhancement tasks.

    S. Korman, R. Litman, S. Avidan, A. M. Bronstein, Probably approximately symmetric: Fast rigid symmetry detection with global guarantees, Computer Graphics Forum (CGF), Vol. 34(1), 2014 details

    Probably approximately symmetric: Fast rigid symmetry detection with global guarantees

    S. Korman, R. Litman, S. Avidan, A. M. Bronstein
    Computer Graphics Forum (CGF), Vol. 34(1), 2014

    We present a fast algorithm for global 3D symmetry detection with approximation guarantees. The algorithm is guaranteed to find the best approximate symmetry of a given shape, to within a user-specified threshold, with very high probability. Our method uses a carefully designed sampling of the transformation space, where each transformation is efficiently evaluated using a sub-linear algorithm. We prove that the density of the sampling depends on the total variation of the shape, allowing us to derive formal bounds on the algorithm’s complexity and approximation quality. We further investigate different volumetric shape representations (in the form of truncated distance transforms), and in such a way control the total variation of the shape and hence the sampling density and the runtime of the algorithm. A comprehensive set of experiments assesses the proposed method, including an evaluation on the eight categories of the COSEG data-set. This is the first large-scale evaluation of any symmetry detection technique that we are aware of.

    R. Litman, A. M. Bronstein, M. M. Bronstein, U. Castellani, Supervised learning of bag-of-features shape descriptors using sparse coding, Computer Graphics Forum (CGF), Vol. 33(5), 2014 details

    Supervised learning of bag-of-features shape descriptors using sparse coding

    R. Litman, A. M. Bronstein, M. M. Bronstein, U. Castellani
    Computer Graphics Forum (CGF), Vol. 33(5), 2014

    We present a method for supervised learning of shape descriptors for shape retrieval applications. Many content-based shape retrieval approaches follow the bag-of-features (BoF) paradigm commonly used in text and image retrieval by first computing local shape descriptors, and then representing them in a `geometric dictionary’ using vector quantization. A major drawback of such approaches is that the dictionary is constructed in an unsupervised manner using clustering, unaware of the last stage of the process (pooling of the local descriptors into a BoF, and comparison of the latter using some metric). In this paper, we replace the clustering with dictionary learning, where every atom acts as a feature, followed by sparse coding and pooling to get the final BoF descriptor. Both the dictionary and the sparse codes can be learned in the supervised regime via bi-level optimization using a task-specific objective that promotes invariance desired in the specific application. We show significant performance improvement on several standard shape retrieval benchmarks.

    O. Menashe, A. M. Bronstein, Real-time compressed imaging of scattering volumes, Proc. Int'l Conf. on Image Processing (ICIP), 2014 details

    Real-time compressed imaging of scattering volumes

    O. Menashe, A. M. Bronstein
    Proc. Int'l Conf. on Image Processing (ICIP), 2014

    We propose a method and a prototype imaging system for real-time reconstruction of volumetric piecewise-smooth scattering media. The volume is illuminated by a sequence of structured binary patterns emitted from a fan beam projector, and the scattered light is collected by a two-dimensional sensor, thus creating an under-complete set of compressed measurements. We show a fixed-complexity and latency reconstruction algorithm capable of estimating the scattering coefficients in real-time. We also show a simple greedy algorithm for learning the optimal illumination patterns. Our results demonstrate faithful reconstruction from highly compressed measurements. Furthermore, a method for compressed registration of the measured volume to a known template is presented, showing excellent alignment with just a single projection. Though our prototype system operates in visible light, the presented methodology is suitable for fast x-ray scattering imaging, in particular in real-time vascular medical imaging.

    S. Biasotti, A. Cerri, A. M. Bronstein, M. M. Bronstein, Quantifying 3D shape similarity using maps: Recent trends, applications and perspectives, Proc. EUROGRAPHICS STARS, 2014 details

    Quantifying 3D shape similarity using maps: Recent trends, applications and perspectives

    S. Biasotti, A. Cerri, A. M. Bronstein, M. M. Bronstein
    Proc. EUROGRAPHICS STARS, 2014

    Shape similarity is an acute issue in Computer Vision and Computer Graphics that involves many aspects of human perception of the real world, including judged and perceived similarity concepts, deterministic and probabilistic decisions and their formalization. 3D models carry multiple information with them (e.g., geometry, topology, texture, time evolution, appearance), which can be thought as the filter that drives the recognition process. Assessing and quantifying the similarity between 3D shapes is necessary to explore large dataset of shapes, and tune the analysis framework to the userÕs needs. Many efforts have been done in this sense, including several attempts to formalize suitable notions of similarity and distance among 3D objects and their shapes. In the last years, 3D shape analysis knew a rapidly growing interest in a number of challenging issues, ranging from deformable shape similarity to partial matching and view-point selection. In this panorama, we focus on methods which quantify shape similarity (between two objects and sets of models) and compare these shapes in terms of their properties (i.e., global and local, geometric, differential and topological) conveyed by (sets of) maps. After presenting in detail the theoretical foundations underlying these methods, we review their usage in a number of 3D shape application domains, ranging from matching and retrieval to annotation and segmentation. Particular emphasis will be given to analyze the suitability of the different methods for specific classes of shapes (e.g. rigid or isometric shapes), as well as the flexibility of the various methods at the different stages of the shape comparison process. Finally, the most promising directions for future research developments are discussed.

    J. Masci, M. M. Bronstein, A. M. Bronstein, J. Schmidhuber, Multimodal similarity-preserving hashing, IEEE Trans. Pattern Analysis and Machine Intelligence (PAMI), Vol. 36(4), 2014 details

    Multimodal similarity-preserving hashing

    J. Masci, M. M. Bronstein, A. M. Bronstein, J. Schmidhuber
    IEEE Trans. Pattern Analysis and Machine Intelligence (PAMI), Vol. 36(4), 2014

    We introduce an efficient computational framework for hashing data belonging to multiple modalities into a single representation space where they become mutually comparable. The proposed approach is based on a novel coupled siamese neural network architecture and allows unified treatment of intra- and inter-modality similarity learning. Unlike existing cross-modality similarity learning approaches, our hashing functions are not limited to binarized linear projections and can assume arbitrarily complex forms. We show experimentally that our method significantly outperforms state-of-the-art hashing approaches on multimedia retrieval tasks.

    J. Masci, A. M. Bronstein, M. M. Bronstein, P. Sprechmann, G. Sapiro, Sparse similarity-preserving hashing, Proc. Int'l Conf. on Learning Representations (ICLR), 2014 details

    Sparse similarity-preserving hashing

    J. Masci, A. M. Bronstein, M. M. Bronstein, P. Sprechmann, G. Sapiro
    Proc. Int'l Conf. on Learning Representations (ICLR), 2014

    In recent years, a lot of attention has been devoted to efficient nearest neighbor search by means of similarity-preserving hashing. One of the plights of existing hashing techniques is the intrinsic trade-off between performance and computational complexity: while longer hash codes allow for lower false positive rates, it is very difficult to increase the embedding dimensionality without incurring in very high false negatives rates or prohibiting computational costs. In this paper, we propose a way to overcome this limitation by enforcing the hash codes to be sparse. Sparse high-dimensional codes enjoy from the low false positive rates typical of long hashes, while keeping the false negative rates similar to those of a shorter dense hashing scheme with equal number of degrees of freedom. We use a tailored feed-forward neural network for the hashing function. Extensive experimental evaluation involving visual and multi-modal data shows the benefits of the proposed method.

    D. Raviv, A. M. Bronstein, M. M. Bronstein, R. Kimmel, N. Sochen, Equi-affine invariant intrinsic geometries for bendable shapes analysis, Journal of Mathematical Imaging and Vision (JMIV), Vol. 50(1), 2014 details

    Equi-affine invariant intrinsic geometries for bendable shapes analysis

    D. Raviv, A. M. Bronstein, M. M. Bronstein, R. Kimmel, N. Sochen
    Journal of Mathematical Imaging and Vision (JMIV), Vol. 50(1), 2014

    Traditional models of bendable surfaces are based on the exact or approximate invariance to deformations that do not tear or stretch the shape, leaving intact an intrinsic geometry associated with it. Intrinsic geometries are typically defined using either the shortest path length (geodesic distance), or properties of heat diffusion (diffusion distance) on the surface. Both ways are implicitly derived from the metric induced by the ambient Euclidean space. In this paper, we depart from this restrictive assumption by observing that a different choice of the metric results in a richer set of geometric invariants. We extend the classic equi-affine arclength, defined on convex surfaces, to arbitrary shapes with non-vanishing gaussian curvature. As a result, a family of affine- invariant intrinsic geometries is obtained. The potential of this novel framework is explored in a wide range of applications such as shape matching and retrieval, symmetry detection, and computation of Voroni tessellation. We show that in some shape analysis tasks, our affine-invariant intrinsic geometries often outperform their Euclidean-based counterparts.

    D. Pickup, X. Sun, P. L. Rosin, R. R. Martin, Z. Cheng, Z. Lian, M. Aono, A. Ben Hamza, A. M. Bronstein, M. M. Bronstein, S. Bu, U. Castellani, S. Cheng, V. Garro, A. Giachetti, A. Godil, J. Han, H. Johan, L. Lai, B. Li, C. Li, H. Li, R. Litman, X. Liu, Z. Liu, Y. Lu, A. Tatsuma, J. Ye, Shape retrieval of non-rigid 3D human models, Proc. EUROGRAPHICS Workshop on 3D Object Retrieval (3DOR), 2014 details

    Shape retrieval of non-rigid 3D human models

    D. Pickup, X. Sun, P. L. Rosin, R. R. Martin, Z. Cheng, Z. Lian, M. Aono, A. Ben Hamza, A. M. Bronstein, M. M. Bronstein, S. Bu, U. Castellani, S. Cheng, V. Garro, A. Giachetti, A. Godil, J. Han, H. Johan, L. Lai, B. Li, C. Li, H. Li, R. Litman, X. Liu, Z. Liu, Y. Lu, A. Tatsuma, J. Ye
    Proc. EUROGRAPHICS Workshop on 3D Object Retrieval (3DOR), 2014

    We have created a new dataset for non-rigid 3D shape retrieval, one that is much more challenging than existing datasets. Our dataset features exclusively human models, in a variety of body shapes and poses. 3D models of humans are commonly used within computer graphics and vision, therefore the ability to distinguish between body shapes is an important feature for shape retrieval methods. In this track nine groups have submitted the results of a total of 22 different methods which have been tested on our new dataset.