Search Results for author: Carlos Fernandez-Granda

Found 28 papers, 16 papers with code

Principled and Efficient Transfer Learning of Deep Models via Neural Collapse

no code implementations23 Dec 2022 Xiao Li, Sheng Liu, Jinxin Zhou, Xinyu Lu, Carlos Fernandez-Granda, Zhihui Zhu, Qing Qu

As model size continues to grow and access to labeled training data remains limited, transfer learning has become a popular approach in many scientific and engineering fields.

Data Augmentation Self-Supervised Learning +1

Avoiding spurious correlations via logit correction

1 code implementation2 Dec 2022 Sheng Liu, Xu Zhang, Nitesh Sekhar, Yue Wu, Prateek Singhal, Carlos Fernandez-Granda

Empirical studies suggest that machine learning models trained with empirical risk minimization (ERM) often rely on attributes that may be spuriously correlated with the class labels.

Evaluating Unsupervised Denoising Requires Unsupervised Metrics

no code implementations11 Oct 2022 Adria Marcos-Morales, Matan Leibovich, Sreyas Mohan, Joshua Lawrence Vincent, Piyush Haluai, Mai Tan, Peter Crozier, Carlos Fernandez-Granda

In this work, we propose two novel metrics: the unsupervised mean squared error (MSE) and the unsupervised peak signal-to-noise ratio (PSNR), which are computed using only noisy data.


Interpretable Prediction of Lung Squamous Cell Carcinoma Recurrence With Self-supervised Learning

1 code implementation23 Mar 2022 Weicheng Zhu, Carlos Fernandez-Granda, Narges Razavian

The resulting representations and clusters from self-supervision are used as features of a survival model for recurrence prediction at the patient level.

Multiple Instance Learning Self-Supervised Learning +1

Deep Probability Estimation

no code implementations21 Nov 2021 Sheng Liu, Aakash Kaku, Weicheng Zhu, Matan Leibovich, Sreyas Mohan, Boyang Yu, Haoxiang Huang, Laure Zanna, Narges Razavian, Jonathan Niles-Weed, Carlos Fernandez-Granda

Reliable probability estimation is of crucial importance in many real-world applications where there is inherent (aleatoric) uncertainty.

Autonomous Vehicles Binary Classification +1

Sequence-to-Sequence Modeling for Action Identification at High Temporal Resolution

1 code implementation3 Nov 2021 Aakash Kaku, Kangning Liu, Avinash Parnandi, Haresh Rengaraj Rajamohan, Kannan Venkataramanan, Anita Venkatesan, Audre Wirtanen, Natasha Pandit, Heidi Schambra, Carlos Fernandez-Granda

To address this, we propose a novel approach for high-resolution action identification, inspired by speech-recognition techniques, which is based on a sequence-to-sequence model that directly predicts the sequence of actions.

Action Recognition speech-recognition +2

Adaptive Early-Learning Correction for Segmentation from Noisy Annotations

2 code implementations CVPR 2022 Sheng Liu, Kangning Liu, Weicheng Zhu, Yiqiu Shen, Carlos Fernandez-Granda

We discover a phenomenon that has been previously reported in the context of classification: the networks tend to first fit the clean pixel-level labels during an "early-learning" phase, before eventually memorizing the false annotations.

Classification Medical Image Segmentation +4

Cramér-Rao bound-informed training of neural networks for quantitative MRI

1 code implementation22 Sep 2021 Xiaoxia Zhang, Quentin Duchemin, Kangning Liu, Sebastian Flassbeck, Cem Gultekin, Carlos Fernandez-Granda, Jakob Assländer

We find, however, that in heterogeneous parameter spaces, i. e. in spaces in which the variance of the estimated parameters varies considerably, good performance is hard to achieve and requires arduous tweaking of the loss function, hyper parameters, and the distribution of the training data in parameter space.

Magnetic Resonance Fingerprinting

Weakly-supervised High-resolution Segmentation of Mammography Images for Breast Cancer Diagnosis

1 code implementation13 Jun 2021 Kangning Liu, Yiqiu Shen, Nan Wu, Jakub Chłędowski, Carlos Fernandez-Granda, Krzysztof J. Geras

In cancer diagnosis, interpretability can be achieved by localizing the region of the input image responsible for the output, i. e. the location of a lesion.

Medical Diagnosis Vocal Bursts Intensity Prediction +1

Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training

1 code implementation NeurIPS 2021 Sheng Liu, Xiao Li, Yuexiang Zhai, Chong You, Zhihui Zhu, Carlos Fernandez-Granda, Qing Qu

Furthermore, we show that our ConvNorm can reduce the layerwise spectral norm of the weight matrices and hence improve the Lipschitzness of the network, leading to easier training and improved robustness for deep ConvNets.

Developing and Evaluating Deep Neural Network-based Denoising for Nanoparticle TEM Images with Ultra-low Signal-to-Noise

no code implementations19 Jan 2021 Joshua L. Vincent, Ramon Manzorro, Sreyas Mohan, Binh Tang, Dev Y. Sheth, Eero P. Simoncelli, David S. Matteson, Carlos Fernandez-Granda, Peter A. Crozier

This shows that the network exploits global and local information in the noisy measurements, for example, by adapting its filtering approach when it encounters atomic-level defects at the nanoparticle surface.

Denoising Materials Science Image and Video Processing

An artificial intelligence system for predicting the deterioration of COVID-19 patients in the emergency department

1 code implementation4 Aug 2020 Farah E. Shamout, Yiqiu Shen, Nan Wu, Aakash Kaku, Jungkyu Park, Taro Makino, Stanisław Jastrzębski, Duo Wang, Ben Zhang, Siddhant Dogra, Meng Cao, Narges Razavian, David Kudlowitz, Lea Azour, William Moore, Yvonne W. Lui, Yindalon Aphinyanaphongs, Carlos Fernandez-Granda, Krzysztof J. Geras

In order to verify performance in a real clinical setting, we silently deployed a preliminary version of the deep neural network at New York University Langone Health during the first wave of the pandemic, which produced accurate predictions in real-time.

COVID-19 Diagnosis Decision Making +1

Early-Learning Regularization Prevents Memorization of Noisy Labels

2 code implementations NeurIPS 2020 Sheng Liu, Jonathan Niles-Weed, Narges Razavian, Carlos Fernandez-Granda

In contrast with existing approaches, which use the model output during early learning to detect the examples with clean labels, and either ignore or attempt to correct the false labels, we take a different route and instead capitalize on early learning via regularization.

General Classification Learning with noisy labels +1

Towards data-driven stroke rehabilitation via wearable sensors and deep learning

no code implementations14 Apr 2020 Aakash Kaku, Avinash Parnandi, Anita Venkatesan, Natasha Pandit, Heidi Schambra, Carlos Fernandez-Granda

Thus, using a combination of IMU-based motion capture and deep learning, we were able to identify primitives automatically.

Be Like Water: Robustness to Extraneous Variables Via Adaptive Feature Normalization

no code implementations10 Feb 2020 Aakash Kaku, Sreyas Mohan, Avinash Parnandi, Heidi Schambra, Carlos Fernandez-Granda

Extraneous variables are variables that are irrelevant for a certain task, but heavily affect the distribution of the available data.

Interpretable and robust blind image denoising with bias-free convolutional neural networks

no code implementations NeurIPS Workshop Deep_Invers 2019 Zahra Kadkhodaie, Sreyas Mohan, Eero P. Simoncelli, Carlos Fernandez-Granda

Here, however, we show that bias terms used in most CNNs (additive constants, including those used for batch normalization) interfere with the interpretability of these networks, do not help performance, and in fact prevent generalization of performance to noise levels not including in the training data.

Image Denoising

Robust and interpretable blind image denoising via bias-free convolutional neural networks

1 code implementation ICLR 2020 Sreyas Mohan, Zahra Kadkhodaie, Eero P. Simoncelli, Carlos Fernandez-Granda

In contrast, a bias-free architecture -- obtained by removing the constant terms in every layer of the network, including those used for batch normalization-- generalizes robustly across noise levels, while preserving state-of-the-art performance within the training range.

Image Denoising

Data-driven Estimation of Sinusoid Frequencies

2 code implementations NeurIPS 2019 Gautier Izacard, Sreyas Mohan, Carlos Fernandez-Granda

Frequency estimation is a fundamental problem in signal processing, with applications in radar imaging, underwater acoustics, seismic imaging, and spectroscopy.

Seismic Imaging

Sparse Recovery Beyond Compressed Sensing: Separable Nonlinear Inverse Problems

no code implementations12 May 2019 Brett Bernstein, Sheng Liu, Chrysa Papadaniil, Carlos Fernandez-Granda

In this work, we consider separable inverse problems, where the data are modeled as a linear combination of functions that depend nonlinearly on certain parameters of interest.


Time-Series Analysis via Low-Rank Matrix Factorization Applied to Infant-Sleep Data

no code implementations9 Apr 2019 Sheng Liu, Mark Cheng, Hayley Brooks, Wayne Mackey, David J. Heeger, Esteban G. Tabak, Carlos Fernandez-Granda

We apply our methodology to detect anomalous individuals, to cluster the cohort into groups with different sleeping tendencies, and to obtain improved predictions of future sleep behavior.

Time Series Time Series Analysis

A Learning-Based Framework for Line-Spectra Super-resolution

1 code implementation14 Nov 2018 Gautier Izacard, Brett Bernstein, Carlos Fernandez-Granda

We propose a learning-based approach for estimating the spectrum of a multisinusoidal signal from a finite number of samples.


Multicompartment Magnetic Resonance Fingerprinting

no code implementations28 Feb 2018 Sunli Tang, Carlos Fernandez-Granda, Sylvain Lannuzel, Brett Bernstein, Riccardo Lattanzi, Martijn Cloos, Florian Knoll, Jakob Assländer

Magnetic resonance fingerprinting (MRF) is a technique for quantitative estimation of spin-relaxation parameters from magnetic-resonance data.

Medical Physics Numerical Analysis Numerical Analysis Optimization and Control

Cannot find the paper you are looking for? You can Submit a new open access paper.