Search Results - "Visin, Francesco"

ReSeg: A Recurrent Neural Network-Based Model for Semantic Segmentation by Visin, Francesco, Romero, Adriana, Kyunghyun Cho, Matteucci, Matteo, Ciccone, Marco, Kastner, Kyle, Bengio, Yoshua, Courville, Aaron

“…We propose a structured prediction architecture, which exploits the local generic features extracted by Convolutional Neural Networks and the capacity of…”
Get full text

Small Data, Big Decisions: Model Selection in the Small-Data Regime by Bornschein, Jorg, Visin, Francesco, Osindero, Simon

“…Proceedings of the International Conference on Machine (ICML 2020) Highly overparametrized neural networks can display curiously strong generalization…”
Get full text

Multi-view Stereo with Single-View Semantic Mesh Refinement by Romanoni, Andrea, Ciccone, Marco, Visin, Francesco, Matteucci, Matteo

“…While 3D reconstruction is a well-established and widely explored research topic, semantic 3D reconstruction has only recently witnessed an increasing share of…”
Get full text

A guide to convolution arithmetic for deep learning by Dumoulin, Vincent, Visin, Francesco

“…We introduce a guide to help deep learning practitioners understand and manipulate convolutional neural network architectures. The guide clarifies the…”
Get full text

Learning rich touch representations through cross-modal self-supervision by Zambelli, Martina, Aytar, Yusuf, Visin, Francesco, Zhou, Yuxiang, Hadsell, Raia

“…The sense of touch is fundamental in several manipulation tasks, but rarely used in robot manipulation. In this work we tackle the problem of learning rich…”
Get full text

ReConvNet: Video Object Segmentation with Spatio-Temporal Features Modulation by Lattari, Francesco, Ciccone, Marco, Matteucci, Matteo, Masci, Jonathan, Visin, Francesco

“…We introduce ReConvNet, a recurrent convolutional architecture for semi-supervised video object segmentation that is able to fast adapt its features to focus…”
Get full text

Continual Unsupervised Representation Learning by Rao, Dushyant, Visin, Francesco, Rusu, Andrei A, Teh, Yee Whye, Pascanu, Razvan, Hadsell, Raia

“…Continual learning aims to improve the ability of modern learning systems to deal with non-stationary distributions, typically by attempting to learn a series…”
Get full text

Meta-Learning with Warped Gradient Descent by Flennerhag, Sebastian, Rusu, Andrei A, Pascanu, Razvan, Visin, Francesco, Yin, Hujun, Hadsell, Raia

“…Learning an efficient update rule from data that promotes rapid learning of new tasks from the same distribution remains an open problem in meta-learning…”
Get full text

Gemma 2: Improving Open Language Models at a Practical Size by Sessa, Pier Giuseppe, Hardin, Cassidy, Bhupatiraju, Surya, Hussenot, Léonard, Shahriari, Bobak, Ramé, Alexandre, Ferret, Johan, Friesen, Abe, Tsitsulin, Anton, Vieillard, Nino, Girgin, Sertan, Hoffman, Matt, Grill, Jean-Bastien, Neyshabur, Behnam, Abdagic, Alvin, Carl, Amanda, Brock, Andy, Paterson, Antonia, Royal, Brandon, Choquette-Choo, Christopher A, Weinberger, David, Vijaykumar, Dimple, Herbison, Dustin, Bandy, Elisa, Wang, Emma, Noland, Eric, Moreira, Erica, Senter, Evan, Eltyshev, Evgenii, Rasskin, Gabriel, Wei, Gary, Cameron, Glenn, Martins, Gus, Hashemi, Hadi, Klimczak-Plucińska, Hanna, Zhou, Jack, Stanway, Jeff, Chan, Jetha, Becker, Jocelyn, Fernandez, Joe, Gordon, Josh, Lipschultz, Josh, Newlan, Josh, Ji, Ju-yeong, Mohamed, Kareem, Badola, Kartikeya, Black, Kat, Millican, Katie, Greene, Kish, Sjoesund, Lars Lowe, Usui, Lauren, Kilpatrick, Logan, Dixon, Lucas, Reid, Machel, Iverson, Mark, Miller, Matt, Rahtz, Matthew, Risdal, Meg, Rahman, Mofi, Khatwani, Mohit, Bardoliwalla, Nenshad, Dumai, Neta, Botarda, Pankil, Barham, Paul, Culliton, Phil, Comanescu, Ramona, Jana, Reena, Agarwal, Rishabh, Saadat, Samaneh, Cogan, Sarah, Perrin, Sarah, Arnold, Sébastien M. R, Krause, Sebastian, Garg, Shruti, Sheth, Shruti, Chan, Susan, Yu, Ting, Kocisky, Tomas, Jain, Vihan, Yadav, Vikas, Meshram, Vilobh, Dharmadhikari, Vishal, Barkley, Warren, Shen, Zhe, Gong, Zhitao, Kirk, Phoebe, Rao, Anand, Warkentin, Tris, Ghahramani, Zoubin, Hadsell, Raia, Banks, Jeanine, Dragan, Anca, Vinyals, Oriol, Dean, Jeff, Kavukcuoglu, Koray, Farabet, Clement, Fiedel, Noah, Kenealy, Kathleen, Dadashi, Robert, Andreev, Alek

“…In this work, we introduce Gemma 2, a new addition to the Gemma family of lightweight, state-of-the-art open models, ranging in scale from 2 billion to 27…”
Get full text

Multi-View Stereo with Single-View Semantic Mesh Refinement by Romanoni, Andrea, Ciccone, Marco, Visin, Francesco, Matteucci, Matteo

“…While 3D reconstruction is a well-established and widely explored research topic, semantic 3D reconstruction has only recently witnessed an increasing share of…”
Get full text

Temporal Difference Uncertainties as a Signal for Exploration by Flennerhag, Sebastian, Wang, Jane X, Sprechmann, Pablo, Visin, Francesco, Galashov, Alexandre, Kapturowski, Steven, Borsa, Diana L, Heess, Nicolas, Barreto, Andre, Pascanu, Razvan

“…An effective approach to exploration in reinforcement learning is to rely on an agent's uncertainty over the optimal policy, which can yield near-optimal…”
Get full text

Mollifying Networks by Gulcehre, Caglar, Moczulski, Marcin, Visin, Francesco, Bengio, Yoshua

“…The optimization of deep neural networks can be more challenging than traditional convex optimization problems due to the highly non-convex nature of the loss…”
Get full text

PixelVAE: A Latent Variable Model for Natural Images by Gulrajani, Ishaan, Kumar, Kundan, Ahmed, Faruk, Taiga, Adrien Ali, Visin, Francesco, Vazquez, David, Courville, Aaron

“…Natural image modeling is a landmark challenge of unsupervised learning. Variational Autoencoders (VAEs) learn a useful latent representation and model global…”
Get full text

ReSeg: A Recurrent Neural Network-based Model for Semantic Segmentation by Visin, Francesco, Ciccone, Marco, Romero, Adriana, Kastner, Kyle, Cho, Kyunghyun, Bengio, Yoshua, Matteucci, Matteo, Courville, Aaron

“…We propose a structured prediction architecture, which exploits the local generic features extracted by Convolutional Neural Networks and the capacity of…”
Get full text

ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks by Visin, Francesco, Kastner, Kyle, Cho, Kyunghyun, Matteucci, Matteo, Courville, Aaron, Bengio, Yoshua

“…In this paper, we propose a deep neural network architecture for object recognition based on recurrent neural networks. The proposed network, called ReNet,…”
Get full text

Theano: A Python framework for fast computation of mathematical expressions by The Theano Development Team, Al-Rfou, Rami, Alain, Guillaume, Almahairi, Amjad, Angermueller, Christof, Bahdanau, Dzmitry, Ballas, Nicolas, Bastien, Frédéric, Bayer, Justin, Belikov, Anatoly, Belopolsky, Alexander, Bengio, Yoshua, Bergeron, Arnaud, Snyder, Josh Bleecher, Bouchard, Nicolas, Bouthillier, Xavier, de Brébisson, Alexandre, Breuleux, Olivier, Carrier, Pierre-Luc, Cho, Kyunghyun, Chorowski, Jan, Christiano, Paul, Cooijmans, Tim, Côté, Marc-Alexandre, Côté, Myriam, Courville, Aaron, Dauphin, Yann N, Delalleau, Olivier, Demouth, Julien, Desjardins, Guillaume, Dieleman, Sander, Ducoffe, Mélanie, Dumoulin, Vincent, Kahou, Samira Ebrahimi, Erhan, Dumitru, Fan, Ziye, Firat, Orhan, Germain, Mathieu, Glorot, Xavier, Graham, Matt, Gulcehre, Caglar, Hamel, Philippe, Harlouchet, Iban, Heng, Jean-Philippe, Hidasi, Balázs, Jain, Arjun, Jean, Sébastien, Jia, Kai, Korobov, Mikhail, Kulkarni, Vivek, Lamb, Alex, Lamblin, Pascal, Larsen, Eric, Laurent, César, Lee, Sean, Lefrancois, Simon, Lemieux, Simon, Léonard, Nicholas, Lin, Zhouhan, Livezey, Jesse A, Lowin, Jeremiah, Manzagol, Pierre-Antoine, Mastropietro, Olivier, McGibbon, Robert T, Memisevic, Roland, van Merriënboer, Bart, Michalski, Vincent, Mirza, Mehdi, Orlandi, Alberto, Pascanu, Razvan, Raffel, Colin, Rocklin, Matthew, Romero, Adriana, Sadowski, Peter, Savard, François, Schlüter, Jan, Schulman, John, Schwartz, Gabriel, Serban, Iulian Vlad, Serdyuk, Dmitriy, Shabanian, Samira, Simon, Étienne, Spieckermann, Sigurd, Subramanyam, S. Ramana, Sygnowski, Jakub, Tanguay, Jérémie, van Tulder, Gijs, Turian, Joseph, Urban, Sebastian, Vincent, Pascal, Visin, Francesco, de Vries, Harm, Warde-Farley, David, Webb, Dustin J, Willson, Matthew, Xu, Kelvin, Xue, Lijun, Yao, Li, Zhang, Saizheng, Zhang, Ying

“…Theano is a Python library that allows to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. Since its…”
Get full text