Search Results - "Ranzato, Marc'aurelio"

DeepFace: Closing the Gap to Human-Level Performance in Face Verification by Taigman, Yaniv, Ming Yang, Ranzato, Marc'Aurelio, Wolf, Lior

“…In modern face recognition, the conventional pipeline consists of four stages: detect => align => represent => classify. We revisit both the alignment step and…”
Get full text

Helpless infants are learning a foundation model by Cusack, Rhodri, Ranzato, Marc’Aurelio, Charvet, Christine J.

“…Human infants are helpless for a protracted period after birth. This has been attributed to maternal constraints causing an early birth while the brain is…”
Get full text

An empirical study of learning rates in deep neural networks for speech recognition by Senior, Andrew, Heigold, Georg, Ranzato, Marc'Aurelio, Ke Yang

“…Recent deep neural network systems for large vocabulary speech recognition are trained with minibatch stochastic gradient descent but use a variety of learning…”
Get full text

Learning invariant features through topographic filter maps by Kavukcuoglu, Koray, Ranzato, Marc'Aurelio, Fergus, Rob, LeCun, Yann

“…Several recently-proposed architectures for high-performance object recognition are composed of two main stages: a feature extraction stage that extracts…”
Get full text

Guest Editorial: Deep Learning by Ranzato, Marc’Aurelio, Hinton, Geoffrey, LeCun, Yann

“…Issue Title: Special Issue: Deep Learning…”
Get full text

The Flores-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation by Goyal, Naman, Gao, Cynthia, Chaudhary, Vishrav, Chen, Peng-Jen, Wenzek, Guillaume, Ju, Da, Krishnan, Sanjana, Ranzato, Marc’Aurelio, Guzmán, Francisco, Fan, Angela

“…One of the biggest challenges hindering progress in low-resource and multilingual machine translation is the lack of good evaluation benchmarks. Current…”
Get full text

Task-Driven Modular Networks for Zero-Shot Compositional Learning by Purushwalkam, Senthil, Nickel, Maximillian, Gupta, Abhinav, Ranzato, Marc'aurelio

“…One of the hallmarks of human intelligence is the ability to compose learned knowledge into novel concepts which can be recognized without a single training…”
Get full text

Web-scale training for face identification by Taigman, Yaniv, Ming Yang, Ranzato, Marc'Aurelio, Wolf, Lior

“…Scaling machine learning methods to very large datasets has attracted considerable attention in recent years, thanks to easy access to ubiquitous sensing and…”
Get full text

PANDA: Pose Aligned Networks for Deep Attribute Modeling by Ning Zhang, Paluri, Manohar, Ranzato, Marc'Aurelio, Darrell, Trevor, Bourdev, Lubomir

“…We propose a method for inferring human attributes (such as gender, hair style, clothes style, expression, action) from images of people under large variation…”
Get full text

What is the best multi-stage architecture for object recognition? by Jarrett, Kevin, Kavukcuoglu, Koray, Ranzato, Marc' Aurelio, LeCun, Yann

“…In many recent object recognition systems, feature extraction stages are generally composed of a filter bank, a non-linear transformation, and some sort of…”
Get full text

On deep generative models with applications to recognition by Ranzato, M., Susskind, J., Mnih, V., Hinton, G.

“…The most popular way to use probabilistic models in vision is first to extract some descriptors of small image patches or object parts using well-engineered…”
Get full text

Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition by Ranzato, M.A., Fu Jie Huang, Boureau, Y.-L., Yann LeCun

“…We present an unsupervised method for learning a hierarchy of sparse feature detectors that are invariant to small shifts and distortions. The resulting…”
Get full text

Modeling Natural Images Using Gated MRFs by Ranzato, M., Mnih, V., Susskind, J. M., Hinton, G. E.

“…This paper describes a Markov Random Field for real-valued image modeling that has two sets of latent variables. One set is used to gate the interactions…”
Get full text

Scale-invariant learning and convolutional networks by Chintala, Soumith, Ranzato, Marc'Aurelio, Szlam, Arthur, Tian, Yuandong, Tygert, Mark, Zaremba, Wojciech

“…Multinomial logistic regression and other classification schemes used in conjunction with convolutional networks (convnets) were designed largely before the…”
Get full text

Modeling pixel means and covariances using factorized third-order boltzmann machines by Ranzato, M A, Hinton, G E

“…Learning a generative model of natural images is a useful way of extracting features that capture interesting regularities. Previous work on learning such…”
Get full text

Hard Mixtures of Experts for Large Scale Weakly Supervised Vision by Gross, Sam, Ranzato, Marc'Aurelio, Szlam, Arthur

“…Training convolutional networks (CNNs) that fit on a single GPU with minibatch stochastic gradient descent has become effective in practice. However, there is…”
Get full text

Efficient Continual Learning with Modular Networks and Task-Driven Priors by Veniat, Tom, Denoyer, Ludovic, Ranzato, Marc'Aurelio

“…Existing literature in Continual Learning (CL) has focused on overcoming catastrophic forgetting, the inability of the learner to recall how to perform tasks…”
Get full text

On Learning Where To Look by Ranzato, Marc'Aurelio

“…Current automatic vision systems face two major challenges: scalability and extreme variability of appearance. First, the computational time required to…”
Get full text

Towards Robust and Efficient Continual Language Learning by Fisch, Adam, Rannen-Triki, Amal, Pascanu, Razvan, Bornschein, Jörg, Lazaridou, Angeliki, Gribovskaya, Elena, Ranzato, Marc'Aurelio

“…As the application space of language models continues to evolve, a natural question to ask is how we can quickly adapt models to new tasks. We approach this…”
Get full text

Asynchronous Local-SGD Training for Language Modeling by Liu, Bo, Chhaparia, Rachita, Douillard, Arthur, Kale, Satyen, Rusu, Andrei A, Shen, Jiajun, Szlam, Arthur, Ranzato, Marc'Aurelio

“…Local stochastic gradient descent (Local-SGD), also referred to as federated averaging, is an approach to distributed optimization where each device performs…”
Get full text