Search Results for author: Shabnam Ghaffarzadegan

Found 11 papers, 5 papers with code

Can Synthetic Data Boost the Training of Deep Acoustic Vehicle Counting Networks?

1 code implementation17 Jan 2024 Stefano Damiano, Luca Bondi, Shabnam Ghaffarzadegan, Andre Guntoro, Toon van Waterschoot

In the design of traffic monitoring solutions for optimizing the urban mobility infrastructure, acoustic vehicle counting models have received attention due to their cost effectiveness and energy efficiency.

Unsupervised Discriminative Learning of Sounds for Audio Event Classification

no code implementations19 May 2021 Sascha Hornauer, Ke Li, Stella X. Yu, Shabnam Ghaffarzadegan, Liu Ren

Recent progress in network-based audio event classification has shown the benefit of pre-training models on visual data such as ImageNet.

Classification Transfer Learning

Improving the Unsupervised Disentangled Representation Learning with VAE Ensemble

no code implementations1 Jan 2021 Nanxiang Li, Shabnam Ghaffarzadegan, Liu Ren

We show both theoretically and experimentally, the VAE ensemble objective encourages the linear transformations connecting the VAEs to be trivial transformations, aligning the latent representations of different models to be "alike".

Disentanglement

Visualizing Classification Structure of Large-Scale Classifiers

1 code implementation12 Jul 2020 Bilal Alsallakh, Zhixin Yan, Shabnam Ghaffarzadegan, Zeng Dai, Liu Ren

We propose a measure to compute class similarity in large-scale classification based on prediction scores.

Classification General Classification

An Ontology-Aware Framework for Audio Event Classification

no code implementations27 Jan 2020 Yiwei Sun, Shabnam Ghaffarzadegan

Recent advancements in audio event classification often ignore the structure and relation between the label classes available as prior information.

Classification General Classification

Disentangled Representation Learning with Sequential Residual Variational Autoencoder

no code implementations ICLR 2020 Nanxiang Li, Shabnam Ghaffarzadegan, Liu Ren

Recent advancements in unsupervised disentangled representation learning focus on extending the variational autoencoder (VAE) with an augmented objective function to balance the trade-off between disentanglement and reconstruction.

Disentanglement

Towards Domain Invariant Heart Sound Abnormality Detection using Learnable Filterbanks

1 code implementation29 Sep 2019 Ahmed Imtiaz Humayun, Shabnam Ghaffarzadegan, Md. Istiaq Ansari, Zhe Feng, Taufiq Hasan

Cardiac auscultation is the most practiced non-invasive and cost-effective procedure for the early diagnosis of heart diseases.

Signal Processing

Self-supervised Attention Model for Weakly Labeled Audio Event Classification

no code implementations7 Aug 2019 Bongjun Kim, Shabnam Ghaffarzadegan

The weakly labeled framework is used to eliminate the need for expensive data labeling procedure and self-supervised attention is deployed to help a model distinguish between relevant and irrelevant parts of a weakly labeled audio clip in a more effective manner compared to prior attention models.

Classification General Classification

Deep Multiple Instance Feature Learning via Variational Autoencoder

no code implementations6 Jul 2018 Shabnam Ghaffarzadegan

MIL is a weakly supervised learning problem where labels are associated with groups of instances (referred as bags) instead of individual instances.

Event Detection Multiple Instance Learning +1

An Ensemble of Transfer, Semi-supervised and Supervised Learning Methods for Pathological Heart Sound Classification

1 code implementation18 Jun 2018 Ahmed Imtiaz Humayun, Md. Tauhiduzzaman Khan, Shabnam Ghaffarzadegan, Zhe Feng, Taufiq Hasan

In this work, we propose an ensemble of classifiers to distinguish between various degrees of abnormalities of the heart using Phonocardiogram (PCG) signals acquired using digital stethoscopes in a clinical setting, for the INTERSPEECH 2018 Computational Paralinguistics (ComParE) Heart Beats SubChallenge.

General Classification Representation Learning +1

Learning Front-end Filter-bank Parameters using Convolutional Neural Networks for Abnormal Heart Sound Detection

1 code implementation15 Jun 2018 Ahmed Imtiaz Humayun, Shabnam Ghaffarzadegan, Zhe Feng, Taufiq Hasan

In this work, we propound a novel CNN architecture that integrates the front-end bandpass filters within the network using time-convolution (tConv) layers, which enables the FIR filter-bank parameters to become learnable.

Anomaly Detection

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