Lucas C. Uzal
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Lucas C. Uzal has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Guillermo L. Grinblat
Universidad Nacional de Rosario UNR-CONICET
3 shared publications - Pablo F. Verdes
CIFASIS, French Argentine International Center for Information and Systems Sciences, UAM (France)/UNR-CONICET (Argentina)
3 shared publications Facundo Tuesca
1 shared publication- Marcos Pividori
Universidad Nacional de Rosario UNR-CONICET
1 shared publication - Pablo M. Granitto
UPCAM (France) / UNR–CONICET (Argentina)
1 shared publication - Rubén D. Piacentini
UNR – CONICET (Argentina)
1 shared publication
Latest Publications
- Open Access
Exploiting GAN Internal Capacity for High-Quality Reconstruction of Natural Images
Generative Adversarial Networks (GAN) have demonstrated impressive results in modeling the distribution of natural images, learning latent representations that capture semantic variations in an unsupervised basis. Beyond the generation of novel samples, it is of special interest to exploit the ability of the GAN generator to model the natural image manifold and hence generate credible changes when manipulating images. However, this line of work is conditioned by the quality of the reconstruction. Until now, only inversion to the latent space has been considered, we propose to exploit the representation in intermediate layers of the generator, and we show that this leads to increased capacity. In particular, we observe that the representation after the first dense layer, present in all state-of-the-art GAN models, is expressive enough to represent natural images with high visual fidelity. It is possible to interpolate around these images obtaining a sequence of new plausible synthetic images that cannot be generated from the latent space. Finally, as an example of potential applications that arise from this inversion mechanism, we show preliminary results in exploiting the learned representation in the attention map of the generator to obtain an unsupervised segmentation of natural images.
Open AccessExploiting GAN Internal Capacity for High-Quality Reconstruction of Natural Images
Generative Adversarial Networks (GAN) have demonstrated impressive results in modeling the distribution of natural images, learning latent representations that capture semantic variations in an unsupervised basis. Beyond the generation of novel samples, it is of special interest to exploit the ability of the GAN generator to model the natural image manifold and hence generate credible changes when manipulating images. However, this line of work is conditioned by the quality of the reconstruction. Until now, only inversion to the latent space has been considered, we propose to exploit the representation in intermediate layers of the generator, and we show that this leads to increased capacity. In particular, we observe that the representation after the first dense layer, present in all state-of-the-art GAN models, is expressive enough to represent natural images with high visual fidelity. It is possible to interpolate around these images obtaining a sequence of new plausible synthetic images that cannot be generated from the latent space. Finally, as an example of potential applications that arise from this inversion mechanism, we show preliminary results in exploiting the learned representation in the attention map of the generator to obtain an unsupervised segmentation of natural images.
- Open Access
Exploiting video sequences for unsupervised disentangling in generative adversarial networks
In this work we present an adversarial training algorithm that exploits correlations in video to learn --without supervision-- an image generator model with a disentangled latent space. The proposed methodology requires only a few modifications to the standard algorithm of Generative Adversarial Networks (GAN) and involves training with sets of frames taken from short videos. We train our model over two datasets of face-centered videos which present different people speaking or moving the head: VidTIMIT and YouTube Faces datasets. We found that our proposal allows us to split the generator latent space into two subspaces. One of them controls content attributes, those that do not change along short video sequences. For the considered datasets, this is the identity of the generated face. The other subspace controls motion attributes, those attributes that are observed to change along short videos. We observed that these motion attributes are face expressions, head orientation, lips and eyes movement. The presented experiments provide quantitative and qualitative evidence supporting that the proposed methodology induces a disentangling of this two kinds of attributes in the latent space.
Open AccessExploiting video sequences for unsupervised disentangling in generative adversarial networks
In this work we present an adversarial training algorithm that exploits correlations in video to learn --without supervision-- an image generator model with a disentangled latent space. The proposed methodology requires only a few modifications to the standard algorithm of Generative Adversarial Networks (GAN) and involves training with sets of frames taken from short videos. We train our model over two datasets of face-centered videos which present different people speaking or moving the head: VidTIMIT and YouTube Faces datasets. We found that our proposal allows us to split the generator latent space into two subspaces. One of them controls content attributes, those that do not change along short video sequences. For the considered datasets, this is the identity of the generated face. The other subspace controls motion attributes, those attributes that are observed to change along short videos. We observed that these motion attributes are face expressions, head orientation, lips and eyes movement. The presented experiments provide quantitative and qualitative evidence supporting that the proposed methodology induces a disentangling of this two kinds of attributes in the latent space.
- 7 October 2014
- Published by Springer Nature in Neural Computing and Applications
- Vol. 26 (3) , 641-649
Nonstationary regression with support vector machines
- 7 October 2014
- Published by Springer Nature in Neural Computing and Applications
- Vol. 26 (3) , 641-649
Nonstationary regression with support vector machines
- 6 June 2012
- Published by Springer Nature in Solar Physics
- Vol. 279 (2) , 551-560
Predictions of the Maximum Amplitude, Time of Occurrence, and Total Length of Solar Cycle 24
- 6 June 2012
- Published by Springer Nature in Solar Physics
- Vol. 279 (2) , 551-560
Predictions of the Maximum Amplitude, Time of Occurrence, and Total Length of Solar Cycle 24
- 25 July 2011
- Published by American Physical Society (APS) in Physical Review E
- Vol. 84 (1) , 016223
Optimal reconstruction of dynamical systems: A noise amplification approach
In this work we propose an objective function to guide the search for a state space reconstruction of a dynamical system from a time series of measurements. These statistics can be evaluated on any reconstructed attractor, thereby allowing a direct comparison among different approaches: (uniform or nonuniform) delay vectors, PCA, Legendre coordinates, etc. It can also be used to select the most appropriate parameters of a reconstruction strategy. In the case of delay coordinates this translates into finding the optimal delay time and embedding dimension from the absolute minimum of the advocated cost function. Its definition is based on theoretical arguments on noise amplification, the complexity of the reconstructed attractor, and a direct measure of local stretch which constitutes an irrelevance measure. The proposed method is demonstrated on synthetic and experimental time series.
- 25 July 2011
- Published by American Physical Society (APS) in Physical Review E
- Vol. 84 (1) , 016223
Optimal reconstruction of dynamical systems: A noise amplification approach
In this work we propose an objective function to guide the search for a state space reconstruction of a dynamical system from a time series of measurements. These statistics can be evaluated on any reconstructed attractor, thereby allowing a direct comparison among different approaches: (uniform or nonuniform) delay vectors, PCA, Legendre coordinates, etc. It can also be used to select the most appropriate parameters of a reconstruction strategy. In the case of delay coordinates this translates into finding the optimal delay time and embedding dimension from the absolute minimum of the advocated cost function. Its definition is based on theoretical arguments on noise amplification, the complexity of the reconstructed attractor, and a direct measure of local stretch which constitutes an irrelevance measure. The proposed method is demonstrated on synthetic and experimental time series.