Search Results for author: Haleh Akrami

Found 14 papers, 3 papers with code

Meta Transfer of Self-Supervised Knowledge: Foundation Model in Action for Post-Traumatic Epilepsy Prediction

no code implementations21 Dec 2023 Wenhui Cui, Haleh Akrami, Ganning Zhao, Anand A. Joshi, Richard M. Leahy

To explore the generalizability of the foundation model in downstream applications, we then apply the model to an unseen TBI dataset for prediction of PTE using zero-shot learning.

Epilepsy Prediction Meta-Learning +2

Learning A Disentangling Representation For PU Learning

no code implementations5 Oct 2023 Omar Zamzam, Haleh Akrami, Mahdi Soltanolkotabi, Richard Leahy

In this paper we propose to learn a neural network-based data representation using a loss function that can be used to project the unlabeled data into two (positive and negative) clusters that can be easily identified using simple clustering techniques, effectively emulating the phenomenon observed in low-dimensional settings.

Clustering Density Estimation +2

Beta quantile regression for robust estimation of uncertainty in the presence of outliers

no code implementations14 Sep 2023 Haleh Akrami, Omar Zamzam, Anand Joshi, Sergul Aydore, Richard Leahy

Outlier features can compromise the performance of deep learning regression problems such as style translation, image reconstruction, and deep anomaly detection, potentially leading to misleading conclusions.

Anomaly Detection Image Reconstruction +3

Toward Improved Generalization: Meta Transfer of Self-supervised Knowledge on Graphs

no code implementations16 Dec 2022 Wenhui Cui, Haleh Akrami, Anand A. Joshi, Richard M. Leahy

Transferring knowledge from a source domain with abundant training data to a target domain is effective for improving representation learning on scarce training data.

Meta-Learning Representation Learning +2

Speech MOS multi-task learning and rater bias correction

no code implementations4 Dec 2022 Haleh Akrami, Hannes Gamper

The mean opinion score (MOS) is standardized for the perceptual evaluation of speech quality and is obtained by asking listeners to rate the quality of a speech sample.

Multi-Task Learning

Learning From Positive and Unlabeled Data Using Observer-GAN

no code implementations26 Aug 2022 Omar Zamzam, Haleh Akrami, Richard Leahy

In our suggested method, the GAN discriminator instructs the generator only to produce samples that fall into the unlabeled data distribution, while a second classifier (observer) network monitors the GAN training to: (i) prevent the generated samples from falling into the positive distribution; and (ii) learn the features that are the key distinction between the positive and negative observations.

Learning from imperfect training data using a robust loss function: application to brain image segmentation

1 code implementation8 Aug 2022 Haleh Akrami, Wenhui Cui, Anand A Joshi, Richard M. Leahy

Segmentation is one of the most important tasks in MRI medical image analysis and is often the first and the most critical step in many clinical applications.

Brain Image Segmentation EEG +4

Semi-supervised Learning using Robust Loss

1 code implementation3 Mar 2022 Wenhui Cui, Haleh Akrami, Anand A. Joshi, Richard M. Leahy

The amount of manually labeled data is limited in medical applications, so semi-supervised learning and automatic labeling strategies can be an asset for training deep neural networks.

Image Classification

Deep Quantile Regression for Uncertainty Estimation in Unsupervised and Supervised Lesion Detection

1 code implementation20 Sep 2021 Haleh Akrami, Anand Joshi, Sergul Aydore, Richard Leahy

Here we address the problem of quantifying uncertainty in the images that are reconstructed by the VAE as the basis for principled outlier or lesion detection.

Anomaly Detection Lesion Detection +2

fMRI-Kernel Regression: A Kernel-based Method for Pointwise Statistical Analysis of rs-fMRI for Population Studies

no code implementations13 Dec 2020 Anand A. Joshi, Soyoung Choi, Haleh Akrami, Richard M. Leahy

While pointwise analysis methods are common in anatomical studies such as cortical thickness analysis and voxel- and tensor-based morphometry and its variants, such a method is lacking for rs-fMRI and could improve the utility of rs-fMRI for group studies.

Time Series Analysis

Addressing Variance Shrinkage in Variational Autoencoders using Quantile Regression

no code implementations18 Oct 2020 Haleh Akrami, Anand A. Joshi, Sergul Aydore, Richard M. Leahy

Using estimated quantiles to compute mean and variance under the Gaussian assumption, we compute reconstruction probability as a principled approach to outlier or anomaly detection.

Anomaly Detection Lesion Detection +1

Robust Variational Autoencoder for Tabular Data with Beta Divergence

no code implementations15 Jun 2020 Haleh Akrami, Sergul Aydore, Richard M. Leahy, Anand A. Joshi

The source of outliers in training data include the data collection process itself (random noise) or a malicious attacker (data poisoning) who may target to degrade the performance of the machine learning model.

Anomaly Detection Data Poisoning

A Pre-defined Sparse Kernel Based Convolution for Deep CNNs

no code implementations2 Oct 2019 Souvik Kundu, Saurav Prakash, Haleh Akrami, Peter A. Beerel, Keith M. Chugg

To explore the potential of this approach, we have experimented with two widely accepted datasets, CIFAR-10 and Tiny ImageNet, in sparse variants of both the ResNet18 and VGG16 architectures.

Robust Variational Autoencoder

no code implementations23 May 2019 Haleh Akrami, Anand A. Joshi, Jian Li, Sergul Aydore, Richard M. Leahy

Machine learning methods often need a large amount of labeled training data.

Outlier Detection

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