Search Results for author: Aaqib Saeed

Found 25 papers, 11 papers with code

Learning behavioral context recognition with multi-stream temporal convolutional networks

no code implementations27 Aug 2018 Aaqib Saeed, Tanir Ozcelebi, Stojan Trajanovski, Johan Lukkien

In this paper, we propose a multi-stream temporal convolutional network to address the problem of multi-label behavioral context recognition.

Feature Engineering Multi-Task Learning

Multi-task Self-Supervised Learning for Human Activity Detection

no code implementations27 Jul 2019 Aaqib Saeed, Tanir Ozcelebi, Johan Lukkien

We learn a multi-task temporal convolutional network to recognize transformations applied on an input signal.

Activity Detection Binary Classification +4

Federated Self-Supervised Learning of Multi-Sensor Representations for Embedded Intelligence

no code implementations25 Jul 2020 Aaqib Saeed, Flora D. Salim, Tanir Ozcelebi, Johan Lukkien

Federated learning provides a compelling framework for learning models from decentralized data, but conventionally, it assumes the availability of labeled samples, whereas on-device data are generally either unlabeled or cannot be annotated readily through user interaction.

Federated Learning Self-Supervised Learning +1

Sense and Learn: Self-Supervision for Omnipresent Sensors

no code implementations28 Sep 2020 Aaqib Saeed, Victor Ungureanu, Beat Gfeller

Likewise, the learned representations with self-supervision are found to be highly transferable between related datasets, even when few labeled instances are available from the target domains.

Continual Learning Few-Shot Learning +3

Contrastive Learning of General-Purpose Audio Representations

2 code implementations21 Oct 2020 Aaqib Saeed, David Grangier, Neil Zeghidour

We introduce COLA, a self-supervised pre-training approach for learning a general-purpose representation of audio.

CoLA Contrastive Learning +2

Damage detection using in-domain and cross-domain transfer learning

no code implementations7 Feb 2021 Zaharah A. Bukhsh, Nils Jansen, Aaqib Saeed

We, therefore, evaluate a combination of in-domain and cross-domain transfer learning strategies for damage detection in bridges.

Transfer Learning

ProcessTransformer: Predictive Business Process Monitoring with Transformer Network

1 code implementation1 Apr 2021 Zaharah A. Bukhsh, Aaqib Saeed, Remco M. Dijkman

Nevertheless, designing a deep neural architecture that performs competitively across various tasks is challenging as existing methods fail to capture long-range dependencies in the input sequences and perform poorly for lengthy process traces.

Management

Federated Self-Training for Semi-Supervised Audio Recognition

1 code implementation14 Jul 2021 Vasileios Tsouvalas, Aaqib Saeed, Tanir Ozcelebi

Notably, we show that with as little as 3% labeled data available, FedSTAR on average can improve the recognition rate by 13. 28% compared to the fully supervised federated model.

Audio Classification Federated Learning

Consistency Training of Multi-exit Architectures for Sensor Data

no code implementations27 Sep 2021 Aaqib Saeed

Deep neural networks have become larger over the years with increasing demand of computational resources for inference; incurring exacerbate costs and leaving little room for deployment on devices with limited battery and other resources for real-time applications.

Multi-Task Learning

The Augmented Image Prior: Distilling 1000 Classes by Extrapolating from a Single Image

1 code implementation1 Dec 2021 Yuki M. Asano, Aaqib Saeed

What can neural networks learn about the visual world when provided with only a single image as input?

Knowledge Distillation

Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Data

no code implementations6 Jun 2022 Shohreh Deldari, Hao Xue, Aaqib Saeed, Jiayuan He, Daniel V. Smith, Flora D. Salim

Unlike existing reviews of SSRL that have pre-dominately focused upon methods in the fields of CV or NLP for a single modality, we aim to provide the first comprehensive review of multimodal self-supervised learning methods for temporal data.

Representation Learning Self-Supervised Learning +2

Binary Early-Exit Network for Adaptive Inference on Low-Resource Devices

no code implementations17 Jun 2022 Aaqib Saeed

Deep neural networks have significantly improved performance on a range of tasks with the increasing demand for computational resources, leaving deployment on low-resource devices (with limited memory and battery power) infeasible.

Audio Classification

Automatic Sleep Scoring from Large-scale Multi-channel Pediatric EEG

1 code implementation30 Jun 2022 Harlin Lee, Aaqib Saeed

But pediatric sleep is severely under-researched compared to adult sleep in the context of machine learning for health, and sleep scoring algorithms developed for adults usually perform poorly on infants.

EEG Electroencephalogram (EEG)

Distilled Non-Semantic Speech Embeddings with Binary Neural Networks for Low-Resource Devices

1 code implementation12 Jul 2022 Harlin Lee, Aaqib Saeed

This work introduces BRILLsson, a novel binary neural network-based representation learning model for a broad range of non-semantic speech tasks.

Emotion Recognition Keyword Spotting +4

COCOA: Cross Modality Contrastive Learning for Sensor Data

1 code implementation31 Jul 2022 Shohreh Deldari, Hao Xue, Aaqib Saeed, Daniel V. Smith, Flora D. Salim

Contrastive Learning (CL) is one of the most well-known approaches in SSL that attempts to learn general, informative representations of data.

Contrastive Learning Self-Supervised Learning

Labeling Chaos to Learning Harmony: Federated Learning with Noisy Labels

1 code implementation19 Aug 2022 Vasileios Tsouvalas, Aaqib Saeed, Tanir Ozcelebi, Nirvana Meratnia

Federated Learning (FL) is a distributed machine learning paradigm that enables learning models from decentralized private datasets, where the labeling effort is entrusted to the clients.

Federated Learning Learning with noisy labels

On Out-of-Distribution Detection for Audio with Deep Nearest Neighbors

1 code implementation27 Oct 2022 Zaharah Bukhsh, Aaqib Saeed

Out-of-distribution (OOD) detection is concerned with identifying data points that do not belong to the same distribution as the model's training data.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +7

Plug-and-Play Multilingual Few-shot Spoken Words Recognition

1 code implementation3 May 2023 Aaqib Saeed, Vasileios Tsouvalas

As technology advances and digital devices become prevalent, seamless human-machine communication is increasingly gaining significance.

Few-Shot Learning Keyword Spotting

Federated Fine-Tuning of Foundation Models via Probabilistic Masking

no code implementations29 Nov 2023 Vasileios Tsouvalas, Yuki Asano, Aaqib Saeed

Foundation Models (FMs) have revolutionized machine learning with their adaptability and high performance across tasks; yet, their integration into Federated Learning (FL) is challenging due to substantial communication overhead from their extensive parameterization.

Federated Learning

Communication-Efficient Federated Learning through Adaptive Weight Clustering and Server-Side Distillation

1 code implementation25 Jan 2024 Vasileios Tsouvalas, Aaqib Saeed, Tanir Ozcelebi, Nirvana Meratnia

Federated Learning (FL) is a promising technique for the collaborative training of deep neural networks across multiple devices while preserving data privacy.

Clustering Federated Learning +2

Learning under Label Noise through Few-Shot Human-in-the-Loop Refinement

no code implementations25 Jan 2024 Aaqib Saeed, Dimitris Spathis, JungWoo Oh, Edward Choi, Ali Etemad

We show that FHLR achieves significantly better performance when learning from noisy labels and achieves state-of-the-art by a large margin, with up to 19% accuracy improvement under symmetric and asymmetric noise.

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