FitNets: Hints for Thin Deep Nets
- Adriana Romero, Nicolas Ballas, S. Kahou, Antoine Chassang, C. Gatta, Yoshua Bengio
- Computer ScienceInternational Conference on Learning…
- 19 December 2014
This paper extends the idea of a student network that could imitate the soft output of a larger teacher network or ensemble of networks, using not only the outputs but also the intermediate representations learned by the teacher as hints to improve the training process and final performance of the student.
Unsupervised Deep Feature Extraction for Remote Sensing Image Classification
- Adriana Romero, C. Gatta, Gustau Camps-Valls
- Computer Science, Environmental ScienceIEEE Transactions on Geoscience and Remote…
- 25 November 2015
The proposed algorithm clearly outperforms standard principal component analysis and its kernel counterpart (kPCA), as well as current state-of-the-art algorithms of aerial classification, while being extremely computationally efficient at learning representations of data.
Standardized evaluation methodology and reference database for evaluating IVUS image segmentation
- S. Balocco, C. Gatta, I. Kakadiaris
- Computer ScienceComput. Medical Imaging Graph.
- 1 March 2014
A Spatially Variant White-Patch and Gray-World Method for Color Image Enhancement Driven by Local Contrast
- E. Provenzi, C. Gatta, Massimo Fierro, A. Rizzi
- Computer ScienceIEEE Transactions on Pattern Analysis and Machine…
- 1 October 2008
It is shown that the combination of a pure WP algorithm (RSR: random spray Retinex) and an essentially GW one (ACE) leads to a more robust and better performing model (RACE), which has a general applicability to perceptually inspired color correction algorithms.
From Retinex to Automatic Color Equalization: issues in developing a new algorithm for unsupervised color equalization
We present a comparison between two color equalization algorithms: Retinex, the famous model due to Land and McCann, and Automatic Color Equalization (ACE), a new algorithm recently presented by the…
SRBF: Speckle reducing bilateral filtering.
- S. Balocco, C. Gatta, O. Pujol, J. Mauri, P. Radeva
- PhysicsUltrasound in Medicine and Biology
- 1 August 2010
ACE: An Automatic Color Equalization Algorithm
A new algorithm for digital images unsupervised enhancement, called ACE for Automatic Color Equalization, based on a new computational approach that merges the "Gray World" and "White Patch" equalization mechanisms, while taking into account the spatial distribution of color information.
Processing of Extremely High-Resolution LiDAR and RGB Data: Outcome of the 2015 IEEE GRSS Data Fusion Contest–Part A: 2-D Contest
- M. Campos-Taberner, Adriana Romero-Soriano, D. Tuia
- Environmental ScienceIEEE Journal of Selected Topics in Applied Earth…
- 8 August 2016
The scientific results obtained by the winners of the 2-D contest are discussed, which studied either the complementarity of RGB and LiDAR with deep neural networks or provided a comprehensive benchmarking evaluation of new classification strategies for extremely high-resolution multimodal data.
...
...