Mohamed Tamaazousti

Dr. Mohamed Tamaazousti


Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 April 2019 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
YTYoussef Tamaazousti
Youssef Tamaazousti
HBHerve Le Borgne
Herve Le Borgne
CHCeline Hudelot
Celine Hudelot
MSMohamed-El-Amine Seddik
Mohamed-El-Amine Seddik
MTMohamed Tamaazousti
Mohamed Tamaazousti
A representation is supposed universal if it encodes any element of the visual world (e.g., objects, scenes) in any configuration (e.g., scale, context). While not expecting pure universal representations, the goal in the literature is to improve the universality level, starting from a representation with a certain level. To improve that universality level, one can diversify the source-task, but it requires many additive annotated data that is costly in terms of manual work and possible expertise. We formalize such a diversification process then propose two methods to improve the universality of CNN representations that limit the need for additive annotated data. The first relies on human categorization knowledge and the second on re-training using fine-tuning. We propose a new aggregating metric to evaluate the universality in a transfer-learning scheme, that addresses more aspects than previous works. Based on it, we show the interest of our methods on 10 target-problems, relating to classification on a variety of visual domains.

1 March 2022 in Journal of Statistical Mechanics: Theory and Experiment
Verified
Journal Article
Closed access
PDF file
VLVincent Lahoche
Vincent Lahoche
DSDine Ousmane Samary
Dine Ousmane Samary
MTMohamed Tamaazousti
Mohamed Tamaazousti
Some recent results showed that the renormalization group (RG) can be considered as a promising framework to address open issues in data analysis. In this work, we focus on one of these aspects, closely related to principal component analysis (PCA) for the case of large dimensional data sets with covariance having a nearly continuous spectrum. In this case, the distinction between ‘noise-like’ and ‘non-noise’ modes becomes arbitrary and an open challenge for standard methods. Observing that both RG and PCA search for simplification for systems involving many degrees of freedom, we aim to use the RG argument to clarify the turning point between noise and information modes. The analogy between coarse-graining renormalization and PCA has been investigated in Bradde and Bialek (2017 J. Stat. Phys. 167 462–75), from a perturbative framework, and the implementation with real sets of data by the same authors showed that the procedure may reflect more than a simple formal analogy. In particular, the separation of sampling noise modes may be controlled by a non-Gaussian fixed point, reminiscent of the behaviour of critical systems. In our analysis, we go beyond the perturbative framework using nonperturbative techniques to investigate non-Gaussian fixed points and propose a deeper formalism allowing us to go beyond power-law assumptions for explicit computations.

23 June 2021 in Entropy
Verified
Journal Article
Open access
PDF file
VLVincent Lahoche
Vincent Lahoche
MOMohamed Ouerfelli
Mohamed Ouerfelli
DSDine Ousmane Samary
Dine Ousmane Samary
MTMohamed Tamaazousti
Mohamed Tamaazousti
The tensorial principal component analysis is a generalization of ordinary principal component analysis focusing on data which are suitably described by tensors rather than matrices. This paper aims at giving the nonperturbative renormalization group formalism, based on a slight generalization of the covariance matrix, to investigate signal detection for the difficult issue of nearly continuous spectra. Renormalization group allows constructing an effective description keeping only relevant features in the low “energy” (i.e., large eigenvalues) limit and thus providing universal descriptions allowing to associate the presence of the signal with objectives and computable quantities. Among them, in this paper, we focus on the vacuum expectation value. We exhibit experimental evidence in favor of a connection between symmetry breaking and the existence of an intrinsic detection threshold, in agreement with our conclusions for matrices, providing a new step in the direction of a universal statement.

28 February 2022 in Symmetry
Verified
Journal Article
Open access
PDF file
VLVincent Lahoche
Vincent Lahoche
DSDine Ousmane Samary
Dine Ousmane Samary
MTMohamed Tamaazousti
Mohamed Tamaazousti
The large scale behavior of systems having a large number of interacting degrees of freedom is suitably described using the renormalization group from non-Gaussian distributions. Renormalization group techniques used in physics are then expected to provide a complementary point of view on standard methods used in data science, especially for open issues. Signal detection and recognition for covariance matrices having nearly continuous spectra is currently an open issue in data science and machine learning. Using the field theoretical embedding introduced in Entropy, 23(9), 1132 to reproduce experimental correlations, we show in this paper that the presence of a signal may be characterized by a phase transition with Z2-symmetry breaking. For our investigations, we use the nonperturbative renormalization group formalism, using a local potential approximation to construct an approximate solution of the flow. Moreover, we focus on the nearly continuous signal build as a perturbation of the Marchenko-Pastur law with many discrete spikes.

31 August 2021 in Entropy
Verified
Journal Article
Open access
PDF file
VLVincent Lahoche
Vincent Lahoche
DSDine Ousmane Samary
Dine Ousmane Samary
MTMohamed Tamaazousti
Mohamed Tamaazousti
Renormalization group techniques are widely used in modern physics to describe the relevant low energy aspects of systems involving a large number of degrees of freedom. Those techniques are thus expected to be a powerful tool to address open issues in data analysis when datasets are highly correlated. Signal detection and recognition for a covariance matrix having a nearly continuous spectra is currently one of these opened issues. First, investigations in this direction have been proposed in recent investigations from an analogy between coarse-graining and principal component analysis (PCA), regarding separation of sampling noise modes as a UV cut-off for small eigenvalues of the covariance matrix. The field theoretical framework proposed in this paper is a synthesis of these complementary point of views, aiming to be a general and operational framework, both for theoretical investigations and for experimental detection. Our investigations focus on signal detection. They exhibit numerical investigations in favor of a connection between symmetry breaking and the existence of an intrinsic detection threshold.

2 March 2017 in IEEE Transactions on Visualization and Computer Graphics
Verified
Journal Article
Closed access
AMAlexandre Morgand
Alexandre Morgand
MTMohamed Tamaazousti
Mohamed Tamaazousti
ABAdrien Bartoli
Adrien Bartoli
Specularities are often problematic in computer vision since they impact the dynamic range of the image intensity. A natural approach would be to predict and discard them using computer graphics models. However, these models depend on parameters which are difficult to estimate (light sources, objects' material properties and camera). We present a geometric model called JOLIMAS: JOint LIght-MAterial Specularity, which predicts the shape of specularities. JOLIMAS is reconstructed from images of specularities observed on a planar surface. It implicitly includes light and material properties, which are intrinsic to specularities. This model was motivated by the observation that specularities have a conic shape on planar surfaces. The conic shape is obtained by projecting a fixed quadric on the planar surface. JOLIMAS thus predicts the specularity using a simple geometric approach with static parameters (object material and light source shape). It is adapted to indoor light sources such as light bulbs and fluorescent lamps. The prediction has been tested on synthetic and real sequences. It works in a multi-light context by reconstructing a quadric for each light source with special cases such as lights being switched on or off. We also used specularity prediction for dynamic retexturing and obtained convincing rendering results. Further results are presented as supplementary video material, which can be found on the Computer Society Digital Library at http://doi.ieeecomputersociety.org/10.1109/TVCG.2017.2677445.